CN114023433A - Early prediction system for predicting severity of acute pancreatitis patient - Google Patents
Early prediction system for predicting severity of acute pancreatitis patient Download PDFInfo
- Publication number
- CN114023433A CN114023433A CN202111155712.7A CN202111155712A CN114023433A CN 114023433 A CN114023433 A CN 114023433A CN 202111155712 A CN202111155712 A CN 202111155712A CN 114023433 A CN114023433 A CN 114023433A
- Authority
- CN
- China
- Prior art keywords
- scale
- patient
- prediction system
- acute pancreatitis
- prediction
- 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
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
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- 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
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Data Mining & Analysis (AREA)
- Biomedical Technology (AREA)
- Pathology (AREA)
- Databases & Information Systems (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Investigating Or Analysing Biological Materials (AREA)
- Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)
Abstract
The invention provides an early prediction system for predicting the severity of an acute pancreatitis patient, and belongs to the field of prediction models. The prediction system is constructed by taking the age, respiratory rate, albumin, Lactate Dehydrogenase (LDH), oxygen support and pleural effusion of an acute pancreatitis patient as prediction indexes. The prediction system is simple in construction method, high in prediction accuracy and discrimination, capable of accurately judging the early severity of the acute pancreatitis patient, accurately judging the probability of the patient developing into severe acute pancreatitis, helping clinicians to obtain the maximum benefit when making clinical decisions, helping the clinicians to make individualized treatment decisions, improving the survival rate of the patients and having wide application prospect.
Description
Technical Field
The invention belongs to the field of prediction models, and particularly relates to an early prediction system for predicting the severity of an acute pancreatitis patient.
Background
Acute Pancreatitis (AP) is a systemic inflammatory response involving multiple organ systems. Most AP patients are milder and usually recover within a week. However, there are also inflammatory reactions in some patients, which are locally spread from the pancreas to the whole body system, affecting the normal functions OF the respective organs, such as respiratory insufficiency, renal insufficiency, circulatory insufficiency (blood pressure lowering or shock), blood coagulation disorder (blood hypercoagulability), etc., and Organ Failure (OF) is caused in severe cases, accompanied by hypoproteinemia, hypocalcemia, etc. OF is the leading cause OF early death in AP patients. The overall mortality rate for AP is between 5-10%. However, if the patient is seriously ill with AP, the death rate is obviously increased and can reach 20 to 40 percent.
According to the Atlanta classification revised 2012, Severe Acute Pancreatitis (SAP) was redefined as AP with Persistent Organ Failure (POF). Research shows that accurate prediction of AP patients in an early stage can carry out active treatment and care measures on the patients as early as possible, such as electrocardiographic monitoring, fluid resuscitation, antibiotic use, abdominocentesis drainage and the like, and all the intervention measures can remarkably improve the complication rate (such as infectious necrosis) and the fatality rate of the AP patients. Therefore, the early accurate judgment of the severity of the SAP patient is of great significance to the reduction of the fatality rate of the patient and the improvement of the prognosis condition of the patient.
Currently, the conventional scoring systems for clinically judging the severity of AP mainly include BISAP, APACHE II, SIRS, Glasgow, SOFA, and the like, but the accuracy of predicting the AP to be developed into SAP by these scoring systems needs to be further improved. Chenqing and the like (establishment of a nomogram for predicting the severity of the first-onset acute pancreatitis, China J. pancreas disease, 2019) disclose a method for establishing a visual nomogram with early prediction value on the severity of the first-onset acute pancreatitis. 706 first-onset AP patients admitted to a hospital within 72h of onset, which are collected by Wenzhou medical university affiliated to the first hospital and are admitted in 2013, 1-2016, are classified into two groups, namely non-severe acute pancreatitis and severe acute pancreatitis, according to the Atlanta classification standard revised in 2012, and general data (age, body weight index, hospital time and the like) and laboratory examination results (blood amylase, blood sugar, albumin, leukocytes, creatinine and urea nitrogen) of the patients are counted and analyzed. Logistic single-factor and multi-factor regression analysis is carried out on the included relevant clinical indexes, a regression equation is obtained according to indexes with statistical difference, a Logistic Regression (LR) model is processed in a visualization mode through R language software to obtain a nomogram, and the sensitivity and the specificity of the model established by the method for predicting the SAP generation are superior to those of urea nitrogen, creatinine and BISAP scores through analysis and verification of a Receiver Operating Characteristic (ROC) curve. However, the nomogram reported in this document mainly has the following problems: (1) the patient admitted within 72h of the disease is included in the prediction model, and the prediction model has no timeliness for the disease with rapid change of the early state of AP acute disease; (2) the predictive model lacks an assessment of the clinical utility of the predictive model, such as decision curve analysis and clinical impact curves; (3) the prediction model lacks prospective test design and multi-center verification, is not strong in popularization from the scientific perspective and is not high in clinical application value; (4) visual applications are not sufficient and inconvenient, lacking in mobile terminal applications.
In order to solve the problems in the prior art, it is of great significance to develop an early prediction system which can be popularized and applied clinically and accurately predict the severity of an acute pancreatitis patient.
Disclosure of Invention
The invention aims to provide an early prediction system which can be popularized and applied clinically and can accurately predict the severity of an acute pancreatitis patient, and the early prediction system has important significance.
The invention provides a prediction system for predicting the severity of an acute pancreatitis patient, which is constructed by taking the age, respiratory rate, albumin, Lactate Dehydrogenase (LDH), oxygen support and pleural effusion of the acute pancreatitis patient as prediction indexes.
Further, the prediction system is an alignment chart, the alignment chart comprises 1 st to 9 th straight lines, and the 1 st to 9 th straight lines are sequentially arranged from top to bottom and are parallel to each other; each straight line represents a scale, and scales are arranged on the scale;
the 1 st scale represents a scale with a score corresponding to the scale on the 2 nd to 7 th scales;
scale 2 indicates age;
the 3 rd scale represents the breathing rate;
scale 4 represents albumin;
the 6 th scale represents oxygen support;
scale 7 indicates pleural effusion;
the 8 th scale represents a scale with the sum of the scores corresponding to the scales on the 2 nd to 7 th scales;
the 9 th scale indicates the probability of the patient developing severe acute pancreatitis.
Furthermore, the scale range of the 1 st scale is 0-100, 0 is at the leftmost end, and 100 is at the rightmost end;
in the 2 nd scale, the age range is 15-80;
in the 3 rd scale, the respiratory frequency range is 10-50;
in the 4 th scale, the albumin range is 25-55;
in the 5 th scale, the LDH range of the lactate dehydrogenase is 0-2600;
in the 6 th scale, the oxygen support range is 0 or 1;
in the 7 th scale, pleural effusion ranged from 0 or 1;
the scale range of the 8 th scale is 0-180, 0 is at the leftmost end, and 180 is at the rightmost end;
in the 9 th scale, the probability that the patient develops severe acute pancreatitis is equal to the scale value corresponding to the sum of scores on the 8 th scale on the 9 th scale, and the range is 0.001-0.999.
Further, in the 2 nd scale, when the age is 15, the corresponding score on the 1 st scale is 0, and when the age is 80, the corresponding score on the 1 st scale is 21;
in the 3 rd scale, when the respiratory rate is 10, the corresponding score on the 1 st scale is 0, and when the respiratory rate is 50, the corresponding score on the 1 st scale is 100;
in scale 4, when albumin is 55, the corresponding score on scale 1 is 0, and when albumin is 25, the corresponding score on scale 1 is 24;
in scale 5, when lactate dehydrogenase LDH is 0, the corresponding score on scale 1 is 0, and when lactate dehydrogenase LDH is 2600, the corresponding score on scale 1 is 50;
in the 6 th scale, when oxygen is supported, 0 is taken, the corresponding score on the 1 st scale is 0, when no oxygen is supported, 1 is taken, and the corresponding score on the 1 st scale is 15;
in the 7 th scale, when having the pleural effusion, take 0, the score that corresponds is 0 on the 1 st scale, when no pleural effusion, takes 1, and the score that corresponds is 13 on the 1 st scale.
Further, the unit of age is year of age, the unit of respiratory rate is counts/min, the unit of albumin is IU/L, and the unit of lactate dehydrogenase LDH is IU/L.
Further, the construction method of the prediction system comprises the following steps:
(1) collecting the prediction index of the acute pancreatitis patient, and inputting the prediction index into an input module;
(2) and (4) constructing a logistic regression model by using the prediction indexes in the input module, and drawing a nomogram.
Further, the acute pancreatitis patient is a patient with abdominal pain within 48 hours of onset.
Further, the prediction system is shown in FIG. 1.
The invention also provides equipment for predicting the severity of the acute pancreatitis patient, which comprises the prediction system.
The invention also provides application of the prediction system in preparing equipment for predicting the severity of patients with acute pancreatitis.
Further, the acute pancreatitis patient is a patient with abdominal pain within 48 hours of onset.
For acute pancreatitis, an acute disease with rapid disease change in the early stage, accurate prediction of the severity of a patient within 48 hours from the onset of abdominal pain to admission is very important. Compared with the prediction system in the prior art, the prediction system provided by the invention is more time-efficient.
Compared with the conventional scoring system (including BISAP, NEWS, APACHE II, SIRS, Glasgow and SOFA) for judging the AP severity clinically at present, the nomogram constructed by the invention has better prediction effect on the probability of the acute pancreatitis patient developing into severe acute pancreatitis; and meanwhile, the method has good clinical utility, has good net income for clinically identifying severe AP patients, and can help clinicians obtain the maximum income when making clinical decisions.
The prediction system provided by the invention has the advantages of simple construction method and high prediction accuracy and discrimination, can accurately judge the early severity of the acute pancreatitis patient, accurately judge the probability of the patient developing into severe acute pancreatitis, is beneficial to guiding doctors to make individualized treatment decisions, and improves the survival rate of the patient.
Obviously, many modifications, substitutions, and variations are possible in light of the above teachings of the invention, without departing from the basic technical spirit of the invention, as defined by the following claims.
The present invention will be described in further detail with reference to the following examples. This should not be understood as limiting the scope of the above-described subject matter of the present invention to the following examples. All the technologies realized based on the above contents of the present invention belong to the scope of the present invention.
Drawings
FIG. 1 is a nomogram constructed in accordance with the present invention to predict the severity of patients with acute pancreatitis.
Fig. 2 shows the area under the working characteristic curve of the subjects of the predictive model in the training queue (A, B), the internal validation queue (C, D) and the external validation queue (E, F), respectively, and the calibration curve. Wherein, A represents that the area of the prediction system under the working characteristic curve of the subject of the training queue is 0.88, B represents that the prediction system has good consistency between the predicted SAP displayed by the calibration curve of the training queue and the actually observed POF, C represents that the area of the prediction system under the working characteristic curve of the subject of the internal verification queue is 0.91, D represents that the prediction system has good consistency between the predicted SAP displayed by the calibration curve of the internal verification queue and the actually observed POF, E represents that the area of the prediction system under the working characteristic curve of the subject of the external verification queue is 0.814, and F represents that the prediction system has good consistency between the predicted SAP displayed by the calibration curve of the external verification queue and the actually observed POF.
Fig. 3 is a clinical utility validation result of the prediction system. Wherein, A represents the clinical decision curve of the prediction system and other clinical scoring systems in the training queue, B represents the clinical influence curve of the prediction system in the training queue for predicting POF, C represents the clinical decision curve of the prediction system and other clinical scoring systems in the internal validation queue, D represents the clinical influence curve of the prediction system in the internal validation queue for predicting POF, E represents the clinical decision curve of the prediction system and other clinical scoring systems in the external validation queue, and F represents the clinical influence curve of the prediction system in the external validation queue for predicting POF.
Fig. 4 is a schematic diagram of a nomogram visualization web calculator.
Detailed Description
The raw materials and equipment used in the invention are known products and are obtained by purchasing commercial products.
Example 1 establishment of an early prediction System for predicting the probability of acute pancreatitis patients developing Severe acute pancreatitis
The early prediction system is a visual nomogram for predicting the probability of acute pancreatitis patients developing severe acute pancreatitis, and the construction method comprises the following steps.
1. Patient data
(1.1) inclusion and exclusion criteria
Inclusion criteria were: (1) a well-diagnosed AP, (2) age 18 to 80 years, (3) onset of abdominal pain to admission time of no more than 48 hours.
Exclusion criteria: patients with severe systemic complications due to AP etiology, such as chronic pancreatitis, pancreatic tumors, trauma or pregnancy.
(1.2) data Source
The method comprises a training queue, an internal verification queue and an external verification queue, and specifically comprises the following steps:
(1) training a queue: a retrospective dataset (for developing early prediction models) from 2009, 1 st 7 to 2013, 30 th 6 th 30 th in washings hospital, university of sichuan, 816 cases total.
(2) Internal validation queue: 398 cases in total are prospective datasets from 2016, 1/2017, 8, 31/year in western hospital, Sichuan university.
(3) External validation queue: 880 cases of acute pancreatitis database from 1 month 2005 to 12 months 2012 of the first subsidiary hospital of Nanchang university.
2. Collecting patient clinical data
Basic clinical information readily available to the patient at the time of routine admission was collected, including basic demographic characteristics such as age, gender, underlying disease (to score Charlson's comorbidity index) and time of onset of abdominal pain prior to admission, vital signs at admission, laboratory parameters (routine blood and biochemical indicators), detailed information on oxygen therapy and presence of pleural effusion.
3. Establishing a visual alignment chart
(3.1) univariate and multivariate logistic regression analysis of prognostic factors
After single-and multi-factor logistic regression analysis (table 1) of all the collected clinical basic information of the training cohort, the independent prognostic factors for POF were found to be the following 6: age (OR 1.03[ 95% CI 1.01-0.05 ]; P ═ 0.01), respiratory rate (1.25[1.10-1.42 ]; P ═ 0.001), albumin (0.92[0.87-0.98 ]; P ═ 0.013), lactate dehydrogenase LDH; 1.002[1.000-1.003 ]; p ═ 0.036), oxygen support (5.17[2.91-9.20 ]; p <0.001) and pleural effusion (3.61[1.97-6.61 ]; p < 0.001).
TABLE 1 univariate and multivariate logistic regression analysis of POF risk factors in training cohorts
(3.2) drawing a visual alignment chart
Based on the above 6 independent prognostic factors, the 6 independent prognostic factors are brought into a multifactor logistic regression model, and an early prediction nomogram for predicting the probability of acute pancreatitis patients developing severe acute pancreatitis is drawn (fig. 1).
As shown in fig. 1, the alignment chart includes 1 st to 9 th straight lines, and the 1 st to 9 th straight lines are sequentially arranged from top to bottom and are parallel to each other; each straight line represents a scale on which there is a scale:
the 1 st scale is a scale with a score corresponding to the scale marks on the 2 nd to 7 th scales, the score range is 0 to 100, 0 is at the leftmost section, and 100 is at the rightmost end;
the 2 nd scale represents the age, ranging from 15 to 80, in units of years; when the age is 15, the corresponding score is 0, and when the age is 80, the corresponding score is 21;
the 3 rd scale represents the respiratory frequency, the range is 10-50, and the unit is times/minute; when the respiratory frequency is 10, the corresponding score is 0, and when the respiratory frequency is 50, the corresponding score is 100;
the 4 th scale represents albumin, the range is 25-55, and the unit is IU/L; when albumin is 55, the corresponding score is 0, and when albumin is 25, the corresponding score is 24;
the 5 th scale represents lactate dehydrogenase LDH, the range is 0-2600, and the unit is IU/L; when lactate dehydrogenase LDH is 0, the corresponding score is 0, and when lactate dehydrogenase LDH is 2600, the corresponding score is 50;
the 6 th scale represents oxygen support and ranges from 0 to 1; if the patient has oxygen support at the time of admission, 0 is taken, and the corresponding score is 0, and if the patient has no oxygen support at the time of admission, 1 is taken, and the corresponding score is 15;
the 7 th scale represents pleural effusion in a range of 0-1; if the patient has pleural effusion when being admitted, 0 is taken, and the corresponding score is 0, and if the patient has no pleural effusion when being admitted, 1 is taken, and the corresponding score is 13;
the 8 th scale represents a scale with the sum of the scores corresponding to the scales on the 2 nd to 7 th scales; the range is 0-180, 0 is at the leftmost end, and 180 is at the rightmost end; the 9 th scale represents the probability of predicting the patient to develop severe acute pancreatitis, ranging from 0.001 to 0.999.
4. Predicting the probability of a validation cohort of patients developing severe acute pancreatitis
The following 6 independent prognostic factors for the patients in the internal validation cohort and the external validation cohort, respectively, were entered into the nomograms constructed in step 3: age, respiratory rate, albumin, lactate dehydrogenase LDH, oxygen support, and pleural effusion, outputting the probability of patients developing severe acute pancreatitis in the internal validation cohort and the external validation cohort.
Embodiment 2 nomogram visualization web calculator
A web calculator for calculating the probability of POF occurrence in the AP patient at the time of admission was prepared based on the calculation formula of the nomogram obtained in example 3, and after 6 independent prognostic factors (age, respiratory rate, albumin, lactate dehydrogenase LDH, oxygen support, and pleural effusion) of the patient to be predicted were inputted, the corresponding predicted probability value could be automatically outputted.
Fig. 4 illustrates: a patient aged 47 years (Age) who was admitted with a respiratory rate (R) of 20/min, Albumin (Albumin)43IU/L, Lactate Dehydrogenase (LDH)257IU/L, and oxygen-supported treatment without pleural effusion, exported a probability of 9.7% of the AP patients developing severe AP.
The following experimental examples demonstrate the prediction effect of the prediction system of the present invention.
Experimental example 1 degree of discrimination and degree of calibration verification
1. Experimental methods
(1) Verifying the discrimination of the model: the area under the subject's working characteristic curve (AUC) was used for evaluation, also called C-index. The larger the AUC, the better the discrimination ability of the prediction model.
(2) Verifying the calibration degree of the model: and drawing a calibration curve, wherein the degree of the calibration of the model is reflected by the closeness degree of the data points to the red solid oblique lines in the graph.
2. Results of the experiment
In the training cohort, the nomogram has a C-index of 0.88 (fig. 2A), and the calibration curve (fig. 2B) for the predicted severe AP shows good agreement with the actual occurrence of POF. In the internal validation cohort, the nomogram used to predict severe AP reached a C-index of 0.91 (fig. 2C) and had better consistency (fig. 2D) than the training cohort. The C-index in the external validation queue was 0.81 (fig. 2E), and the calibration curve also showed satisfactory consistency (fig. 2F).
The experimental results show that the prediction model established by the invention has excellent discrimination and calibration.
Experimental example 2 comparison of the prediction System of the present invention with a conventional clinical prognosis scoring System
1. Experimental methods
AUC, sensitivity, specificity, Positive Likelihood Ratio (PLR), Negative Likelihood Ratio (NLR) and posterior probability of subject performance profiles of the predictive system of example 1 of the invention and conventional clinical scoring systems (including BISAP, NEWS, APACHE II, SIRS, Glasgow, SOFA) were compared.
Clinical utility (DCA) of the predictive system of example 1 of the invention was compared to conventional clinical scoring systems (including BISAP, NEWS, APACHE II, SIRS, Glasgow, SOFA), and the net benefit (CIC) clinically used to identify SAP patients.
2. Results of the experiment
TABLE 2 comparison of POF prediction values for nomograms and clinical prognosis scoring systems of the present invention
In table 2, PLR represents a positive likelihood ratio, which is a ratio of a true positive rate to a false positive rate of the screening results. Indicating that the likelihood of a screening test being positive correctly is a multiple of the likelihood of a false positive. The greater the ratio, the greater the probability that the test result is positive, true positive. NLR represents the negative likelihood ratio, which is the ratio of false negative rate and true negative rate of the screening result. The probability of showing a negative false judgment is a multiple of the probability of correctly judging a negative. The smaller the ratio, the more likely it is that the test result is negative and true negative. When PLR >10 or NLR <0.1, diagnosis can be essentially determined or excluded.
In the training, internal validation and external validation cohorts, 9.8% (80/816), 7.5% (30/398) and 20.2% (178/880) of patients actually developed POF, respectively.
The predicted effect of BISAP on POF was best (AUC 0.89[0.87-0.91], PLR 7.24), followed by nomograms of the invention (AUC 0.88[0.86-0.91], PLR4.26) in the training cohort (Table 2), and both were superior to APACHE II (0.79[0.76-0.82], PLR 3.61) and Glasgow (0.75[0.72-0.78], PLR 2.89) (P < 0.05).
In the internal validation cohort (table 2), the nomograms of the invention showed the best predictive effect (AUC0.91[0.88-0.94], PLR 7.89), and outperformed all other clinical scoring systems (P < 0.05); next NEWS (0.79[0.75-0.83], PLR 2.80) and BISAP (0.75[0.71-0.79], PLR 5.72); in addition, the NLR (0.11) of the nomogram is best in all systems, and the posterior probability of POF (0.9%) is lowest, so that the negative predictive value of the nomogram is highest, the prediction efficiency of predicting that a patient does not develop SAP is the highest by using the nomogram, and the occurrence of severe acute pancreatitis of the patient can be clinically excluded to the greatest extent.
In the external validation cohort (Table 2), the nomograms of the invention likewise had the highest AUC (0.81[0.79-0.84]), the lowest NLR (0.29) and the post-test probability of no POF (6.7%), and the AUC of the nomograms of the invention was higher than NEWS, BISAP, APACHE II and SIRS (P < 0.05).
In addition, the nomograms of the training cohort (fig. 3A, B), the internal validation cohort (fig. 3C, D), and the external validation cohort (fig. 3E, F) showed better or equal clinical utility compared to other prognostic scoring systems, and had good clinical net benefit for identifying critically ill AP patients. Of particular note, the inventive nomogram outperformed all other prognostic scoring systems in the internal validation cohort, suggesting that the inventive nomogram may help clinicians gain maximum benefit in making clinical decisions because it shows more benefit than the extreme case of diagnosing POF or not diagnosing POF in all patients.
The results show that compared with the conventional scoring system (including BISAP, NEWS, APACHE II, SIRS, Glasgow and SOFA) which is clinically used at present for judging the severity of AP, the nomogram constructed by the invention has better prediction effect on the probability of acute pancreatitis patients developing severe acute pancreatitis; and meanwhile, the method has good clinical utility, has good net income for clinically identifying severe AP patients, and can help clinicians obtain the maximum income when making clinical decisions.
In conclusion, the early prediction system for predicting the severity of the acute pancreatitis patient, which can be popularized and applied clinically, is simple in construction method and high in prediction accuracy and discrimination, can accurately judge the early severity of the acute pancreatitis patient, accurately judge the probability of the patient developing into severe acute pancreatitis, help clinicians to obtain the maximum benefit when making clinical decisions, help guiding doctors to make individualized treatment decisions, and improve the survival rate of the patients.
Claims (10)
1. A prediction system for predicting the severity of a patient with acute pancreatitis, comprising: the prediction system is constructed by taking the age, respiratory rate, albumin, Lactate Dehydrogenase (LDH), oxygen support and pleural effusion of the acute pancreatitis patient as prediction indexes.
2. The prediction system of claim 1, wherein: the prediction system is an alignment chart, the alignment chart comprises 1 st to 9 th straight lines, and the 1 st to 9 th straight lines are sequentially arranged from top to bottom and are mutually parallel; each straight line represents a scale, and scales are arranged on the scale;
the 1 st scale represents a scale with a score corresponding to the scale on the 2 nd to 7 th scales;
scale 2 indicates age;
the 3 rd scale represents the breathing rate;
scale 4 represents albumin;
scale 5 indicates lactate dehydrogenase LDH;
the 6 th scale represents oxygen support;
scale 7 indicates pleural effusion;
the 8 th scale represents a scale with the sum of the scores corresponding to the scales on the 2 nd to 7 th scales;
the 9 th scale indicates the probability of the patient developing severe acute pancreatitis.
3. The prediction system of claim 2, wherein: the scale range of the 1 st scale is 0-100, 0 is at the leftmost end, and 100 is at the rightmost end;
in the 2 nd scale, the age range is 15-80;
in the 3 rd scale, the respiratory frequency range is 10-50;
in the 4 th scale, the albumin range is 25-55;
in the 5 th scale, the LDH range of the lactate dehydrogenase is 0-2600;
in the 6 th scale, the oxygen support range is 0 or 1;
in the 7 th scale, pleural effusion ranged from 0 or 1;
the scale range of the 8 th scale is 0-180, 0 is at the leftmost end, and 180 is at the rightmost end;
in the 9 th scale, the probability that the patient develops severe acute pancreatitis is equal to the scale value corresponding to the sum of scores on the 8 th scale on the 9 th scale, and the range is 0.001-0.999.
4. The prediction system of claim 3, wherein: in the 2 nd scale, when the age is 15, the corresponding score on the 1 st scale is 0, and when the age is 80, the corresponding score on the 1 st scale is 21;
in the 3 rd scale, when the respiratory rate is 10, the corresponding score on the 1 st scale is 0, and when the respiratory rate is 50, the corresponding score on the 1 st scale is 100;
in scale 4, when albumin is 55, the corresponding score on scale 1 is 0, and when albumin is 25, the corresponding score on scale 1 is 24;
in scale 5, when lactate dehydrogenase LDH is 0, the corresponding score on scale 1 is 0, and when lactate dehydrogenase LDH is 2600, the corresponding score on scale 1 is 50;
in the 6 th scale, when oxygen is supported, 0 is taken, the corresponding score on the 1 st scale is 0, when no oxygen is supported, 1 is taken, and the corresponding score on the 1 st scale is 15;
in the 7 th scale, when having the pleural effusion, take 0, the score that corresponds is 0 on the 1 st scale, when no pleural effusion, takes 1, and the score that corresponds is 13 on the 1 st scale.
5. The prediction system of claim 4, wherein: age is in units of years, respiratory rate is in units of counts/min, albumin is in units of IU/L, and lactate dehydrogenase LDH is in units of IU/L.
6. The prediction system of claim 1, wherein: the construction method of the prediction system comprises the following steps:
(1) collecting the prediction index of the acute pancreatitis patient, and inputting the prediction index into an input module;
(2) and (4) constructing a logistic regression model by using the prediction indexes in the input module, and drawing a nomogram.
7. The prediction system according to any one of claims 1 to 6, wherein: the acute pancreatitis patient is a patient with abdominal pain within 48 hours of onset.
8. The prediction system according to any one of claims 1 to 6, wherein: the prediction system shown is shown in figure 1.
9. An apparatus for predicting the severity of a patient with acute pancreatitis, comprising: the apparatus comprising a prediction system as claimed in any one of claims 1 to 8.
10. Use of a prediction system according to any one of claims 1 to 8 in the manufacture of a device for predicting the severity of a patient with acute pancreatitis; preferably, the acute pancreatitis patient is a patient with abdominal pain onset within 48 hours.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111155712.7A CN114023433A (en) | 2021-09-29 | 2021-09-29 | Early prediction system for predicting severity of acute pancreatitis patient |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111155712.7A CN114023433A (en) | 2021-09-29 | 2021-09-29 | Early prediction system for predicting severity of acute pancreatitis patient |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114023433A true CN114023433A (en) | 2022-02-08 |
Family
ID=80055283
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111155712.7A Pending CN114023433A (en) | 2021-09-29 | 2021-09-29 | Early prediction system for predicting severity of acute pancreatitis patient |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114023433A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115331819A (en) * | 2022-07-29 | 2022-11-11 | 中国医学科学院北京协和医院 | Pancreatitis prognosis data processing method and system based on artificial intelligence |
| CN115472289A (en) * | 2022-08-10 | 2022-12-13 | 浙江大学 | Method for improving clinical severity score prediction efficiency |
| CN116741384A (en) * | 2023-08-14 | 2023-09-12 | 惠民县人民医院 | Bedside care-based severe acute pancreatitis clinical data management method |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111312387A (en) * | 2020-01-16 | 2020-06-19 | 安徽医科大学第一附属医院 | Model for predicting severity of pain of male chronic prostatitis/chronic pelvic pain syndrome and establishment of model |
-
2021
- 2021-09-29 CN CN202111155712.7A patent/CN114023433A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111312387A (en) * | 2020-01-16 | 2020-06-19 | 安徽医科大学第一附属医院 | Model for predicting severity of pain of male chronic prostatitis/chronic pelvic pain syndrome and establishment of model |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115331819A (en) * | 2022-07-29 | 2022-11-11 | 中国医学科学院北京协和医院 | Pancreatitis prognosis data processing method and system based on artificial intelligence |
| CN115472289A (en) * | 2022-08-10 | 2022-12-13 | 浙江大学 | Method for improving clinical severity score prediction efficiency |
| CN115472289B (en) * | 2022-08-10 | 2023-05-16 | 浙江大学 | Method for improving clinical severity score prediction efficacy |
| CN116741384A (en) * | 2023-08-14 | 2023-09-12 | 惠民县人民医院 | Bedside care-based severe acute pancreatitis clinical data management method |
| CN116741384B (en) * | 2023-08-14 | 2023-11-21 | 惠民县人民医院 | Bedside care-based severe acute pancreatitis clinical data management method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Liu et al. | Prognostic accuracy of the serum lactate level, the SOFA score and the qSOFA score for mortality among adults with Sepsis | |
| Williams et al. | Systemic inflammatory response syndrome, quick sequential organ function assessment, and organ dysfunction: insights from a prospective database of ED patients with infection | |
| CN114023433A (en) | Early prediction system for predicting severity of acute pancreatitis patient | |
| Olsson et al. | Comparison of the rapid emergency medicine score and APACHE II in nonsurgical emergency department patients | |
| Schneider et al. | Predicting acute kidney injury among burn patients in the 21st century: a classification and regression tree analysis | |
| CN105229471A (en) | For determining the system and method for preeclampsia risk based on biochemical biomarker analysis | |
| Melis et al. | Validation of the Surgical Apgar Score in a veteran population undergoing general surgery | |
| CN114317532B (en) | Evaluation gene set, kit, system and application for predicting leukemia prognosis | |
| Phungoen et al. | Emergency Severity Index as a predictor of in-hospital mortality in suspected sepsis patients in the emergency department | |
| Sikka et al. | A comparison of severity of illness scoring systems for elderly patients with severe pneumonia | |
| Martín‐Rodríguez et al. | Accuracy of prehospital point‐of‐care lactate in early in‐hospital mortality | |
| Neyra et al. | Prediction of mortality and major adverse kidney events in critically ill patients with acute kidney injury | |
| Matsuhashi et al. | A simple prediction score for in-hospital mortality in patients with nonvariceal upper gastrointestinal bleeding | |
| CN115101199A (en) | Interpretable fair early death risk assessment model and device for critically ill elderly patients and establishment method thereof | |
| CN116013516A (en) | Death risk prediction system and method for sepsis-related acute kidney injury | |
| Bawore et al. | A pattern of platelet indices as a potential marker for prediction of pre-eclampsia among pregnant women attending a Tertiary Hospital, Ethiopia: A case-control study | |
| CN116259410A (en) | Liver cancer occurrence risk prediction model and construction method of network calculator thereof | |
| Zolotov et al. | Can renal parameters predict the mortality of hospitalized COVID-19 patients? | |
| Verma et al. | Performance profile of an outcome measure: morbidity assessment index for newborns | |
| CN114566284A (en) | Disease prognosis risk prediction model training method and device and electronic equipment | |
| CN115223706A (en) | Sepsis early stage screening model suitable for mobile monitoring equipment | |
| Shi et al. | Predicting persistent organ failure on admission in patients with acute pancreatitis: development and validation of a mobile nomogram | |
| Zhong et al. | Analysis of risk factors associated with different degrees of postpartum hemorrhage in patients with pregnancy-induced hypertension and construction of a prediction model using line graph | |
| Wu et al. | Prediction differences and implications of acute kidney injury with and without urine output criteria in adult critically ill patients | |
| Xing et al. | Enhancing gestational diabetes mellitus risk assessment and treatment through GDMPredictor: a machine learning approach |
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 |