CN113209402A - Risk prediction system and equipment for liver cirrhosis accompanied with spontaneous peritonitis - Google Patents
Risk prediction system and equipment for liver cirrhosis accompanied with spontaneous peritonitis Download PDFInfo
- Publication number
- CN113209402A CN113209402A CN202110571409.9A CN202110571409A CN113209402A CN 113209402 A CN113209402 A CN 113209402A CN 202110571409 A CN202110571409 A CN 202110571409A CN 113209402 A CN113209402 A CN 113209402A
- Authority
- CN
- China
- Prior art keywords
- model
- parameters
- prediction
- drainage
- risk
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 206010034674 peritonitis Diseases 0.000 title claims abstract description 33
- 208000019425 cirrhosis of liver Diseases 0.000 title claims abstract description 27
- 230000002269 spontaneous effect Effects 0.000 title claims abstract description 26
- 238000004458 analytical method Methods 0.000 claims description 23
- 206010003445 Ascites Diseases 0.000 claims description 21
- 206010016654 Fibrosis Diseases 0.000 claims description 17
- 230000007882 cirrhosis Effects 0.000 claims description 17
- 238000011156 evaluation Methods 0.000 claims description 16
- 239000007788 liquid Substances 0.000 claims description 16
- 238000012216 screening Methods 0.000 claims description 11
- 238000007477 logistic regression Methods 0.000 claims description 10
- 238000000605 extraction Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 9
- 238000004891 communication Methods 0.000 claims description 7
- 238000000034 method Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000007637 random forest analysis Methods 0.000 claims description 6
- OYPRJOBELJOOCE-UHFFFAOYSA-N Calcium Chemical compound [Ca] OYPRJOBELJOOCE-UHFFFAOYSA-N 0.000 claims description 5
- 102000007584 Prealbumin Human genes 0.000 claims description 5
- 108010071690 Prealbumin Proteins 0.000 claims description 5
- 102100027378 Prothrombin Human genes 0.000 claims description 5
- 108010094028 Prothrombin Proteins 0.000 claims description 5
- 238000008050 Total Bilirubin Reagent Methods 0.000 claims description 5
- 210000004369 blood Anatomy 0.000 claims description 5
- 239000008280 blood Substances 0.000 claims description 5
- 229910052791 calcium Inorganic materials 0.000 claims description 5
- 239000011575 calcium Substances 0.000 claims description 5
- 238000000546 chi-square test Methods 0.000 claims description 5
- 229940039716 prothrombin Drugs 0.000 claims description 5
- 238000012706 support-vector machine Methods 0.000 claims description 5
- 238000003066 decision tree Methods 0.000 claims description 4
- 230000000452 restraining effect Effects 0.000 claims description 4
- 238000012353 t test Methods 0.000 claims description 4
- 238000000585 Mann–Whitney U test Methods 0.000 claims description 3
- 238000000692 Student's t-test Methods 0.000 claims description 3
- 238000000556 factor analysis Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 230000006870 function Effects 0.000 description 9
- 210000000683 abdominal cavity Anatomy 0.000 description 8
- 238000012360 testing method Methods 0.000 description 6
- 210000001015 abdomen Anatomy 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 3
- 201000010099 disease Diseases 0.000 description 3
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 3
- 230000000968 intestinal effect Effects 0.000 description 3
- 206010020772 Hypertension Diseases 0.000 description 2
- 238000012512 characterization method Methods 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000035622 drinking Effects 0.000 description 2
- 208000006454 hepatitis Diseases 0.000 description 2
- 231100000283 hepatitis Toxicity 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000000391 smoking effect Effects 0.000 description 2
- 241000894006 Bacteria Species 0.000 description 1
- 206010057573 Chronic hepatic failure Diseases 0.000 description 1
- 208000035473 Communicable disease Diseases 0.000 description 1
- 208000010334 End Stage Liver Disease Diseases 0.000 description 1
- 208000027761 Hepatic autoimmune disease Diseases 0.000 description 1
- 208000005176 Hepatitis C Diseases 0.000 description 1
- 206010021036 Hyponatraemia Diseases 0.000 description 1
- 208000031662 Noncommunicable disease Diseases 0.000 description 1
- 208000032023 Signs and Symptoms Diseases 0.000 description 1
- 206010046274 Upper gastrointestinal haemorrhage Diseases 0.000 description 1
- LEHOTFFKMJEONL-UHFFFAOYSA-N Uric Acid Chemical compound N1C(=O)NC(=O)C2=C1NC(=O)N2 LEHOTFFKMJEONL-UHFFFAOYSA-N 0.000 description 1
- TVWHNULVHGKJHS-UHFFFAOYSA-N Uric acid Natural products N1C(=O)NC(=O)C2NC(=O)NC21 TVWHNULVHGKJHS-UHFFFAOYSA-N 0.000 description 1
- 230000003187 abdominal effect Effects 0.000 description 1
- 230000001476 alcoholic effect Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000023555 blood coagulation Effects 0.000 description 1
- 230000036772 blood pressure Effects 0.000 description 1
- 230000001684 chronic effect Effects 0.000 description 1
- 208000011444 chronic liver failure Diseases 0.000 description 1
- 238000003759 clinical diagnosis Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 206010012601 diabetes mellitus Diseases 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 238000013399 early diagnosis Methods 0.000 description 1
- 239000003792 electrolyte Substances 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 210000001035 gastrointestinal tract Anatomy 0.000 description 1
- 208000007386 hepatic encephalopathy Diseases 0.000 description 1
- 208000002672 hepatitis B Diseases 0.000 description 1
- 208000015181 infectious disease Diseases 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000003907 kidney function Effects 0.000 description 1
- 210000004185 liver Anatomy 0.000 description 1
- 208000019423 liver disease Diseases 0.000 description 1
- 230000003908 liver function Effects 0.000 description 1
- 210000004698 lymphocyte Anatomy 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008506 pathogenesis Effects 0.000 description 1
- 230000035699 permeability Effects 0.000 description 1
- 239000012466 permeate Substances 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000004393 prognosis Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 230000005236 sound signal Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
- 229940116269 uric acid Drugs 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/50—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H70/00—ICT specially adapted for the handling or processing of medical references
- G16H70/60—ICT specially adapted for the handling or processing of medical references relating to pathologies
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
- A61M2205/00—General characteristics of the apparatus
- A61M2205/18—General characteristics of the apparatus with alarm
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
- A61M2205/00—General characteristics of the apparatus
- A61M2205/33—Controlling, regulating or measuring
- A61M2205/3331—Pressure; Flow
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention belongs to the technical field of liver cirrhosis medical equipment, and particularly discloses a risk prediction system and equipment for liver cirrhosis accompanied with spontaneous peritonitis. By adopting the technical scheme, the clinical index parameters are obtained by utilizing the cooperation of all the units, the prediction parameters are obtained according to the clinical index parameters, then the prediction parameters of the person to be tested are obtained, and whether the person to be tested generates spontaneous peritonitis is predicted, so that early warning on the spontaneous peritonitis is realized.
Description
Technical Field
The invention belongs to the technical field of liver cirrhosis medical equipment, and relates to a risk prediction system and equipment for liver cirrhosis accompanied with spontaneous peritonitis.
Background
Ascites formation is a manifestation of liver cirrhosis entering the decompensation stage, and if ascites soaks the intestinal canal for a long time, the intestinal wall is damaged, the permeability is increased, and bacteria in the intestinal tract permeate to the abdominal cavity through the intestinal wall to cause spontaneous peritonitis. Idiopathic peritonitis (SBP) is an ascites infection that occurs without a source of infection in the abdominal cavity, adjacent tissues, and is a serious complication of advanced liver disease and chronic severe hepatitis. SBP has been found to occur at a rate of 10% to 30% in patients with liver cirrhosis and is one of the leading causes of death in end-stage liver disease. Compared with cirrhosis patients without infectious diseases, the death probability of the infected cirrhosis patients is 4 times higher, the hospitalization mortality rate is 30-50%, and the recurrence rate of SBP in the cirrhosis patients with SBP history is up to 40-70% within one year.
Early clinical diagnosis is difficult due to atypical, few symptoms, or other symptoms and signs common to disease. Although much research has been done clinically on the pathogenesis, diagnosis and treatment of SBP, there are certain difficulties in its early diagnosis and prognosis. The research utilizes common clinical indexes of patients with cirrhosis to establish Logistic regression, random forest, decision tree, support vector machine and extreme gradient promotion five machine learning models, and explores the prediction value of each model on the diagnosis of early spontaneous peritonitis.
Disclosure of Invention
The invention aims to provide a risk prediction system and equipment for cirrhosis accompanied with spontaneous peritonitis, which can be used for realizing risk prediction of spontaneous peritonitis, screening clinical index parameters and improving prediction accuracy.
In order to achieve the purpose, the basic scheme of the invention is as follows: a risk prediction system for cirrhosis with idiopathic peritonitis, comprising:
the data acquisition unit is used for acquiring clinical index parameters of the sample;
the data processing unit is used for carrying out single-factor analysis on the clinical index parameters and screening to obtain baseline characteristic parameters;
the screening unit is used for constructing at least one analysis model by utilizing the baseline characteristic parameters and acquiring prediction parameters through the analysis model;
and the prediction unit acquires the prediction parameters of the person to be tested, inputs the prediction parameters of the person to be tested into the analysis model and obtains the prediction result of whether spontaneous peritonitis occurs.
The working principle and the beneficial effects of the basic scheme are as follows: the data acquisition unit can acquire clinical index parameters of the samples and is used for constructing a prediction model. The data processing unit is used for preprocessing the data and analyzing the single factor, preliminarily screening meaningful data, removing the meaningless data, simplifying the data type and utilizing subsequent identification of causes of diseases. The screening unit is used for screening the prediction parameters and predicting by only using the prediction parameters, so that the problems of low operation speed, poor performance and the like of the prediction model caused by excessive model indexes are solved. The prediction unit predicts whether the person to be detected generates spontaneous peritonitis according to the prediction parameters of the person to be detected, is simple and convenient to operate, and achieves early warning of the spontaneous peritonitis so as to treat the spontaneous peritonitis in time.
Further, the system also comprises a model evaluation unit, wherein the model evaluation unit stores quota evaluation parameters: the model evaluation unit acquires corresponding data of the analysis model, compares the acquired data value with a rated evaluation parameter to obtain a comparison difference value, and evaluates the prediction performance of the analysis model according to the comparison difference value.
And evaluating each item of data of the prediction model by using a model evaluation unit so as to judge the operational performance of the prediction model, so that the prediction model is optimized at a later stage, and meanwhile, the reliability of the prediction model is judged.
Further, the analysis model adopts a Logistic regression model, a random forest model, a decision tree model, a support vector machine model or a limiting gradient lifting model.
And selecting a proper analysis model according to the requirement, so that the use is facilitated.
Further, the specific treatment method comprises the following steps: the Logistic regression and XGboost model joint operation:
classifying the baseline characteristic parameters into height risk parameters and general risk parameters, and inputting the baseline characteristic parameters into an XGboost model after classification;
performing XGboost model training, respectively solving probability distribution conditions of the altitude risk parameters and the general risk parameters in the training process, setting loss function weights according to the probability distribution conditions, and training the altitude risk parameters and the general risk parameters at intervals, so that the model can quickly realize the prediction speed of various samples;
and (4) outputting the XGboost model in a probabilistic mode by using a logistic function to prevent misprediction.
Further, chi-square test is adopted for counting data in the clinical index parameters, t test is carried out on data which obey normal distribution in the metering data of the clinical index parameters, and Mann-Whitney U test is adopted for data which do not obey normal distribution in the metering data of the clinical index parameters.
And (3) carrying out targeted processing and analysis on the clinical index parameters, and screening out factors which have great influence on the result of predicting the spontaneous peritonitis.
Further, the prediction parameters include prealbumin, blood calcium, total bilirubin, and prothrombin time.
The influence of the parameters on the spontaneous peritonitis is large, and the prediction model judges whether the sample has the spontaneous peritonitis according to the parameters, so that the judgment accuracy is higher.
The invention also provides ascites due to cirrhosis extraction equipment, which comprises the risk prediction system, a restraining belt and a drainage device;
the two ends of the binding belt are respectively connected to the two reels, the reels are connected with a power source for controlling the rotation of the binding belt, a pressure sensor is arranged on the side surface of the binding belt, which is in contact with a human body, the output end of the pressure sensor is connected with a controller, the output end of the controller is connected with the control end of the reels, the two reels are connected through a connecting rod to form a placing opening, a drainage device can puncture the human body from the placing opening to conduct ascites drainage, a valve is arranged at the placing opening, and the control end of the valve is connected with the output end of a;
the drainage device comprises a drainage needle cylinder and a drainage needle, wherein the side wall of the drainage needle cylinder is communicated with a liquid storage box, a first one-way valve which is communicated in the liquid storage box in a one-way mode is arranged at the communication position of the drainage needle cylinder and the liquid storage box, and a second one-way valve which is communicated in the drainage needle cylinder in the one-way mode is arranged at the communication position of the drainage needle cylinder and the drainage needle cylinder.
After the abdominal cavity is subjected to ascites extraction, the binding belt is favorable for increasing abdominal pressure, and the abdominal cavity is prevented from rising again. The pressure sensor is arranged on the binding belt and used for detecting the pressure between the binding belt and the abdomen, the pressure sensor transmits a pressure signal to the controller, the controller controls the reel to rotate, automatic control over tensioning of the binding belt is achieved, manual operation is not needed, and the use is convenient. Place the mouth department and set up the valve, only open when needing, do benefit to the use, avoid the constraint area to have the breach for a long time and be unfavorable for compressing tightly the belly.
Set up first check valve and second check valve on the drainage ware, realize once inserting the abdominal cavity and extract ascites many times, prior art needs make the drainage ware insert the abdominal cavity again after taking off drainage ascites with the drainage syringe, repeats many times and can realize the ascites extraction, and above-mentioned scheme need not to insert the abdominal cavity repeatedly, reduces patient's discomfort and to patient's damage.
Furthermore, one end of the drainage needle cylinder close to the drainage needle is communicated with the top of the liquid storage box, and the liquid storage box is positioned below the drainage needle cylinder.
The structure arrangement is beneficial to discharging the ascites in the drainage syringe into the liquid storage box, and simultaneously, the ascites in the liquid storage box is prevented from flowing back to the drainage syringe.
Further, the system also comprises an alarm which is connected with the output end of the risk prediction system, and the alarm is arranged on the binding belt or a remote terminal.
Whether to carry out alarm is selected according to the output signal of the risk prediction system, so that medical personnel and patients can quickly obtain alarm signals to timely treat the disease.
Drawings
FIG. 1 is a schematic flow diagram of a risk prediction system for cirrhosis with idiopathic peritonitis according to the present invention;
FIG. 2 is a schematic structural view of the ascites due to cirrhosis extracting apparatus of the present invention;
FIG. 3 is a histogram of the results of a random forest model of the risk prediction system for cirrhosis with idiopathic peritonitis of the present invention;
FIG. 4 is a schematic diagram of the XGboost model index importance result of the risk prediction system for liver cirrhosis accompanied by spontaneous peritonitis.
Reference numerals in the drawings of the specification include: the binding belt comprises a binding belt 1, a shell 2, a placing opening 3 and a connecting rod 4.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
In the description of the present invention, it is to be understood that the terms "longitudinal", "lateral", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", and the like, indicate orientations or positional relationships based on those shown in the drawings, and are used merely for convenience of description and for simplicity of description, and do not indicate or imply that the referenced devices or elements must have a particular orientation, be constructed in a particular orientation, and be operated, and thus, are not to be construed as limiting the present invention.
In the description of the present invention, unless otherwise specified and limited, it is to be noted that the terms "mounted," "connected," and "connected" are to be interpreted broadly, and may be, for example, a mechanical connection or an electrical connection, a communication between two elements, a direct connection, or an indirect connection via an intermediate medium, and specific meanings of the terms may be understood by those skilled in the art according to specific situations.
As shown in FIG. 1, the invention discloses a risk prediction system for liver cirrhosis accompanied with spontaneous peritonitis, which comprises a data acquisition unit, a data processing unit, a screening unit and a prediction unit.
The data acquisition unit is used for acquiring clinical index parameters of the sample, wherein the clinical index parameters comprise etiology, such as related indexes of hepatitis B, hepatitis C, alcoholic liver, biliary hepatitis, autoimmune liver disease and the like; common complications of SBP, such as upper gastrointestinal hemorrhage, hepatic encephalopathy, hyponatremia, and other related indicators; other data related indexes, such as blood routine, liver function, renal function, electrolyte, blood coagulation function index, etc.; general data, such as sex, age, smoking history, drinking history, whether hypertension is present, whether diabetes is present, and the like. Preferably, the index with deletion rate > 30% in the clinical index parameter is deleted.
And the data processing unit performs single factor analysis on the clinical index parameters and screens the clinical index parameters to obtain baseline characteristic parameters. The baseline characteristic parameters comprise 39 indexes such as gender, hospitalization days, smoking, drinking, decompensation period, lymphocyte percentage, calcium, total bilirubin, uric acid, prealbumin, prothrombin time, international standardized ratio and the like. According to whether the sample has spontaneous peritonitis, the clinical index parameters are divided into two groups, wherein the group with the spontaneous peritonitis is the first group, and the group without the spontaneous peritonitis is the second group. The counting data in the clinical index parameters are expressed by adopting rate and percentage and pass chi square test which is also called chi square test2The test is a hypothesis test method, and the basic formula of the test is as follows:
a is an actual number, T is a theoretical number deduced according to a test hypothesis, and the obtained characteristic parameters are shown in Table 1.
TABLE 1 Baseline characterization parameters for chi-square test
And (4) expressing data which obey normal distribution in the metering data of the clinical index parameters by adopting X +/-S, and carrying out t test. the t-test is also called Student's t test and is mainly used for the sample with small content (such as n)<30) The overall standard deviation σ is an unknown normal distribution. Median and interquartile M (Q) for data not normally distributed in measurement data of clinical index parameters25～Q75) Expressed and tested by Mann-Whitney U(Mann-Whitney rank sum test), the Mann-Whitney U test belongs to one of the non-parametric tests, which assume that two samples are respectively from two populations that are identical except for the population mean, in order to test whether the mean of the two populations differ significantly. The measurement data is data of blood pressure, height and the like, and the data can be directly used for measuring the size. The counting data is data such as gender and whether hypertension exists, and is used for measuring the number of the data. The baseline characteristic parameters in the metrology data for the clinical index parameters are shown in table 2.
TABLE 2 Baseline characterization parameters of metrology data
The screening unit constructs at least one analysis model by using the baseline characteristic parameters, and obtains the prediction parameters through the analysis model. The prediction parameters include prealbumin, blood calcium, total bilirubin, and prothrombin time. And (3) dividing the prediction parameters in the group I into a training set and an internal verification set according to the proportion of 7:3, taking the training set as an input variable, and taking whether spontaneous peritonitis occurs as an outcome variable of the analysis model to construct the analysis model. The analysis model adopts a Logistic regression model, a random forest model, a decision tree model, a support vector machine model or a limit gradient lifting model. Compared with a Logistic regression model and an XGboost model with better performance, the time of prealbumin, blood calcium, total bilirubin and prothrombin is found to be obvious in the two models by combining an OR value and a gain value.
The specific treatment method comprises the following steps: the Logistic regression and XGboost model joint operation can be adopted:
and classifying the baseline characteristic parameters into height risk parameters and general risk parameters, and inputting the baseline characteristic parameters into the XGboost model after classification.
The XGboost model is trained, in the training process, probability distribution conditions are respectively obtained for altitude risk parameters and general risk parameters, loss function weights are set according to the probability distribution conditions, the risk parameters can be specifically grouped according to the probability distribution conditions, the loss function weight with large probability distribution is large, the loss function weight with small probability distribution is small, the loss function weight with large probability distribution is larger than that of the general risk parameters, and the altitude risk parameters and the general risk parameters are trained at intervals, so that the model can quickly realize the prediction speed of various samples.
And finally, outputting the XGboost model in a probabilistic mode by using a logistic function to prevent misprediction.
The regression results using the Logistic regression model are shown in table 3, the analysis results using the random forest model are shown in fig. 3, and the index importance analysis results of the support vector machine model (XGBoost model) are shown in fig. 4.
TABLE 3 Logistic regression model results
The prediction unit collects the prediction parameters of the person to be tested, and inputs the prediction parameters of the person to be tested into the analysis model to obtain the prediction result of whether spontaneous peritonitis occurs. The output value range of the prediction model is [0,1], if the output value is less than or equal to 0.5, the etiology type is predicted to be non-infectious diseases, and if the output value is more than 0.5, the possibility of infecting spontaneous peritonitis is predicted.
In a preferred embodiment of the present invention, the risk prediction system further includes a model evaluation unit, and the model evaluation unit stores an amount evaluation parameter: the model evaluation unit collects corresponding data of the analysis model, compares the collected data value with a rated evaluation parameter to obtain a comparison difference value, and evaluates the prediction performance of the analysis model according to the comparison difference value.
As shown in figure 2, the invention also provides ascites due to cirrhosis extraction equipment, which comprises the risk prediction system, the restraining belt 1 and the drainage device, wherein when the extraction equipment works, the prediction system is always in a working state, so that the safe extraction is ensured.
Two ends of the binding belt 1 are respectively connected to the two reels, the end parts of the binding belt 1 are respectively welded with the corresponding reels, the reels rotate, and the binding belt 1 can be wound on the reels. The binding belt 1 can be a whole belt body or formed by connecting two belt bodies, when the whole belt body is arranged, the binding belt 1 is directly sleeved on the body of a patient along the head or the feet of the patient and moves to the abdomen of the patient; when setting up two areas body, the spool that corresponds is connected respectively to the one end of two areas bodies, and the other end of two areas bodies passes through devices such as buckle and can dismantle the connection each other. The reel is connected with a power source for controlling the reel to rotate, the power source is preferably a motor, and an output shaft of the motor is coaxially mounted with the reel. The side face of the binding belt 1, which is contacted with a human body, is provided with a pressure sensor, the output end of the pressure sensor is electrically connected with a controller, and the output end of the controller is electrically connected with the control end of the scroll.
Preferably, the controller includes a comparator, a first input end of the comparator is electrically connected with the pressure threshold memory, a second input end of the comparator is electrically connected with an output end of the pressure sensor, and an output end of the comparator is electrically connected with a control end of the motor. When the pressure signal detected by the pressure sensor is smaller than the pressure signal in the pressure threshold value memory, the comparator outputs a control signal to the control end of the motor to control the motor to start, and the motor drives the reel to rotate to tighten the binding belt 1. More preferably, two control buttons are arranged on the side wall of the motor, and the control buttons are respectively and electrically connected with the positive rotation control end and the negative rotation control end of the motor and are used for controlling the motor to rotate.
The two reels are connected through the connecting rod 4 to form the placing opening 3, the shell 2 is arranged on the outer side of each reel, the motor can be mounted on the shell 2, the reels are rotatably connected onto the shell 2, the connecting rods 4 are at least two, the end parts of the connecting rods 4 are hinged or welded with the shell 2 respectively, and the placing opening 3 is formed by surrounding the connecting rods 4 and the shell 2. The drainage ware can be from placing mouthful 3 human bodies of puncture and carrying out the ascites drainage, and it is equipped with the valve to place mouthful 3 departments, the control end of valve and risk prediction system's output electric connection, and the side of preferred valve is equipped with control switch, and control switch's output and the control end electric connection of valve for manual control valve's switching uses more in a flexible way.
The drainage device comprises a drainage needle cylinder and a drainage needle, the side wall of the drainage needle cylinder is communicated with a liquid storage box, a first one-way valve which is communicated in the liquid storage box in a one-way mode is arranged at the communication position of the drainage needle cylinder and the liquid storage box, and a second one-way valve which is communicated in the drainage needle cylinder in the one-way mode is arranged at the communication position of the drainage needle cylinder and the drainage needle cylinder. One end of the drainage needle cylinder close to the drainage needle is communicated with the top of the liquid storage box, and the liquid storage box is positioned below the drainage needle cylinder. When the drainage needle is inserted into the abdominal cavity, the push rod on the drainage needle cylinder is pulled to begin to extract ascites, then the push rod is pushed again to push the ascites in the drainage needle cylinder into the liquid storage box, and the operation is repeated for several times to realize ascites extraction.
In a preferred embodiment of the present invention, the ascites due to cirrhosis extracting device further comprises an alarm (not shown), the alarm is electrically connected (e.g. wirelessly or by wire) with the output end of the risk prediction system, and the alarm is disposed on the restraining belt 1 or the remote terminal. The alarm can be preferably an LED lamp or a buzzer and the like, is used for emitting sound signals or light signals, and the emitted signals are simple and clear and are also beneficial to installation and use.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the invention have been shown and described, it will be understood by those of ordinary skill in the art that: various changes, modifications, substitutions and alterations can be made to the embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.
Claims (9)
1. A system for risk prediction of cirrhosis with idiopathic peritonitis, comprising:
the data acquisition unit is used for acquiring clinical index parameters of the sample;
the data processing unit is used for carrying out single-factor analysis on the clinical index parameters and screening to obtain baseline characteristic parameters;
the screening unit is used for constructing at least one analysis model by utilizing the baseline characteristic parameters and acquiring prediction parameters through the analysis model;
and the prediction unit acquires the prediction parameters of the person to be tested, inputs the prediction parameters of the person to be tested into the analysis model and obtains the prediction result of whether spontaneous peritonitis occurs.
2. The system of claim 1, further comprising a model evaluation unit, wherein the model evaluation unit stores an amount evaluation parameter: the model evaluation unit acquires corresponding data of the analysis model, compares the acquired data value with a rated evaluation parameter to obtain a comparison difference value, and evaluates the prediction performance of the analysis model according to the comparison difference value.
3. The system of claim 1, wherein the analytical model is a Logistic regression model, or a random forest model, or a decision tree model, or a support vector machine model, or a limiting gradient elevation model.
4. The system for predicting risk of cirrhosis with idiopathic peritonitis according to claim 3, wherein the specific treatment method is: the Logistic regression and XGboost model joint operation:
classifying the baseline characteristic parameters into height risk parameters and general risk parameters, and inputting the baseline characteristic parameters into an XGboost model after classification;
performing XGboost model training, respectively solving probability distribution conditions of the altitude risk parameters and the general risk parameters in the training process, setting loss function weights according to the probability distribution conditions, and training the altitude risk parameters and the general risk parameters at intervals, so that the model can quickly realize the prediction speed of various samples;
and (4) outputting the XGboost model in a probabilistic mode by using a logistic function to prevent misprediction.
5. The system of claim 1, wherein the clinical index parameter is subjected to a chi-square test for the count data, the clinical index parameter is subjected to a t-test for the data that obeys normal distribution in the count data, and the clinical index parameter is subjected to a Mann-Whitney U-test for the data that does not obey normal distribution in the count data.
6. The system of claim 1, wherein the prediction parameters include prealbumin, blood calcium, total bilirubin, and prothrombin time.
7. A ascites due to cirrhosis extraction device, characterized by comprising a risk prediction system according to any one of claims 1 to 6, a restraining strip and a flow diverter;
the two ends of the binding belt are respectively connected to the two reels, the reels are connected with a power source for controlling the rotation of the binding belt, a pressure sensor is arranged on the side surface of the binding belt, which is in contact with a human body, the output end of the pressure sensor is connected with a controller, the output end of the controller is connected with the control end of the reels, the two reels are connected through a connecting rod to form a placing opening, a drainage device can puncture the human body from the placing opening to conduct ascites drainage, a valve is arranged at the placing opening, and the control end of the valve is connected with the output end of a risk prediction system;
the drainage device comprises a drainage needle cylinder and a drainage needle, wherein the side wall of the drainage needle cylinder is communicated with a liquid storage box, a first one-way valve which is communicated in the liquid storage box in a one-way mode is arranged at the communication position of the drainage needle cylinder and the liquid storage box, and a second one-way valve which is communicated in the drainage needle cylinder in the one-way mode is arranged at the communication position of the drainage needle cylinder and the drainage needle cylinder.
8. The ascites due to cirrhosis extracting apparatus according to claim 7, wherein an end of the drainage syringe adjacent to the drainage needle communicates with a top portion of a reservoir located below the drainage syringe.
9. The ascites due to cirrhosis extraction device of claim 7, further comprising an alarm connected to an output of the risk prediction system, the alarm being provided on a leash, or on a remote terminal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110571409.9A CN113209402A (en) | 2021-05-25 | 2021-05-25 | Risk prediction system and equipment for liver cirrhosis accompanied with spontaneous peritonitis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110571409.9A CN113209402A (en) | 2021-05-25 | 2021-05-25 | Risk prediction system and equipment for liver cirrhosis accompanied with spontaneous peritonitis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113209402A true CN113209402A (en) | 2021-08-06 |
Family
ID=77098373
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110571409.9A Pending CN113209402A (en) | 2021-05-25 | 2021-05-25 | Risk prediction system and equipment for liver cirrhosis accompanied with spontaneous peritonitis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113209402A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113730080A (en) * | 2021-10-18 | 2021-12-03 | 重庆医科大学 | Colorectal cancer patient postoperative care device and prediction system |
| CN113995587A (en) * | 2021-10-27 | 2022-02-01 | 重庆医科大学 | Acute myocardial infarction intervention postoperative care device and risk prediction system |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1973778A (en) * | 2006-12-08 | 2007-06-06 | 南京大学 | Method of predicting serious complication risk degree after gastric cancer operation |
| CN206342723U (en) * | 2016-08-23 | 2017-07-21 | 信泽涛 | Internal medicine flow diverter |
| CN108430427A (en) * | 2015-10-16 | 2018-08-21 | 佐尔循环服务系统公司 | Automate chest compression device |
| CN109473175A (en) * | 2018-11-07 | 2019-03-15 | 中山大学附属第三医院（中山大学肝脏病医院） | A kind of Noninvasive serology Rating Model and its design method for liver fibrosis |
| CN210277818U (en) * | 2019-04-14 | 2020-04-10 | 阿依努尔 | Drainage device for respiratory medicine |
| CN111388773A (en) * | 2020-03-26 | 2020-07-10 | 邢树员 | Clinical hematocele-preventing drainage operation device for neurosurgery |
| CN111529770A (en) * | 2020-05-09 | 2020-08-14 | 刘艳娟 | Intelligence abdominal cavity ponding drainage system |
| CN111991634A (en) * | 2020-09-21 | 2020-11-27 | 苏州市立医院 | Ascites treatment device |
| CN212327052U (en) * | 2019-12-04 | 2021-01-12 | 孙巍玲 | Ascites drainage device for gastroenterology |
| CN213131084U (en) * | 2020-04-21 | 2021-05-07 | 吉林大学第一医院 | Fixed firm tumour ponding drainage ware of rubber tube |
-
2021
- 2021-05-25 CN CN202110571409.9A patent/CN113209402A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1973778A (en) * | 2006-12-08 | 2007-06-06 | 南京大学 | Method of predicting serious complication risk degree after gastric cancer operation |
| CN108430427A (en) * | 2015-10-16 | 2018-08-21 | 佐尔循环服务系统公司 | Automate chest compression device |
| CN206342723U (en) * | 2016-08-23 | 2017-07-21 | 信泽涛 | Internal medicine flow diverter |
| CN109473175A (en) * | 2018-11-07 | 2019-03-15 | 中山大学附属第三医院（中山大学肝脏病医院） | A kind of Noninvasive serology Rating Model and its design method for liver fibrosis |
| CN210277818U (en) * | 2019-04-14 | 2020-04-10 | 阿依努尔 | Drainage device for respiratory medicine |
| CN212327052U (en) * | 2019-12-04 | 2021-01-12 | 孙巍玲 | Ascites drainage device for gastroenterology |
| CN111388773A (en) * | 2020-03-26 | 2020-07-10 | 邢树员 | Clinical hematocele-preventing drainage operation device for neurosurgery |
| CN213131084U (en) * | 2020-04-21 | 2021-05-07 | 吉林大学第一医院 | Fixed firm tumour ponding drainage ware of rubber tube |
| CN111529770A (en) * | 2020-05-09 | 2020-08-14 | 刘艳娟 | Intelligence abdominal cavity ponding drainage system |
| CN111991634A (en) * | 2020-09-21 | 2020-11-27 | 苏州市立医院 | Ascites treatment device |
Non-Patent Citations (5)
| Title |
|---|
| 何雨芯 等: "慢加急性肝衰竭合并自发性细菌性腹膜炎影响因素分析与预测模型构建", 《现代预防医学》, vol. 48, no. 8, 30 April 2021 (2021-04-30), pages 1354 - 1358 * |
| 谈军涛 等: "基于机器学习算法的肝硬化相关肝性脑病预测模型的构建", 《解放军医学杂志》 * |
| 谈军涛 等: "基于机器学习算法的肝硬化相关肝性脑病预测模型的构建", 《解放军医学杂志》, vol. 46, no. 4, 28 April 2021 (2021-04-28), pages 354 - 360 * |
| 陈宗海, 合肥：中国科学技术大学出版社 * |
| 陈宗海, 合肥：中国科学技术大学出版社, pages: 395 - 397 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113730080A (en) * | 2021-10-18 | 2021-12-03 | 重庆医科大学 | Colorectal cancer patient postoperative care device and prediction system |
| CN113995587A (en) * | 2021-10-27 | 2022-02-01 | 重庆医科大学 | Acute myocardial infarction intervention postoperative care device and risk prediction system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Morgan et al. | Measurements of stressed states in the field | |
| CN113209402A (en) | Risk prediction system and equipment for liver cirrhosis accompanied with spontaneous peritonitis | |
| CN101535497A (en) | Method of determining hypoxia in scalp blood during labour | |
| CN111305338A (en) | Disease early warning system based on excrement ecological evaluation, health monitoring ring and closestool | |
| US20230096779A1 (en) | Toilet, testing, and monitoring systems | |
| CN109085163A (en) | A kind of Novel urine testing and analysis system | |
| CN208140719U (en) | A kind of blood glucose meter test paper and the storage box and recycling box | |
| CN105455795A (en) | Animal physiological information display device and method | |
| CN205720260U (en) | The long-range Urine Analyzer of domestic | |
| CN207133293U (en) | A kind of portable feces occult blood detector | |
| CN112835316A (en) | Neonatal sepsis shock prediction system and monitoring equipment | |
| CN202305531U (en) | Fecal occult blood detecting device | |
| CN104569437B (en) | For assessing the test kit of women twenty-four-hour urine sodium value | |
| CN115327138A (en) | Portable fecal occult blood detection device | |
| CN209117584U (en) | Urine detector capable of providing health information for medical block chain | |
| CN213902985U (en) | Cleanliness detection equipment | |
| CN112002414A (en) | Gastric juice cognition-based stomach disease system, equipment and storage medium | |
| CN113380329A (en) | Prediction system and device for resistance of first injection gamma globulin of Kawasaki disease patient child | |
| WO2021222076A1 (en) | Interfering flag to reduce falses diagnosis due to interfering conditions in microscopic morphology based sediment urinalysis | |
| EP3702781A1 (en) | Installable system for regular continual analysis of an individual's urine to determine the level of hydration of said individual | |
| WO2024069600A1 (en) | A fluid collection device | |
| KR20160003479U (en) | This feature combined with containers for urine test urine samples | |
| KR100608434B1 (en) | Concentration measured apparatus and method thereof of oral gas | |
| EP1933707B1 (en) | Method for monitoring a childbirth process | |
| CN114681249B (en) | Multifunctional detection nursing bed and danger prediction system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210806 |
|
| RJ01 | Rejection of invention patent application after publication |