Prediction system for predicting severity of pregnancy acute pancreatitis patient

Abstract

The invention provides a prediction system for predicting severity of a patient with acute pancreatitis of pregnancy, and belongs to the field of prediction models. The prediction system is constructed by taking albumin and urea nitrogen levels of patients with acute pancreatitis of pregnancy as prediction indexes. The prediction system is simple in construction method, high in prediction accuracy and distinction degree, capable of accurately judging the probability of the severity of the acute pancreatitis patients during pregnancy, helpful for clinicians to obtain the maximum income when making clinical decisions, helpful for guiding the clinicians to make individualized treatment decisions and improving the survival rate of the acute pancreatitis patients during pregnancy, and wide in application prospect.

Description

Technical Field

[0001] The present invention belongs to the field of prediction models, and in particular relates to a prediction system for predicting the severity of patients with acute pancreatitis during pregnancy. Background Art

[0002] Currently, there are multiple prediction systems for assessing the severity of acute pancreatitis, including the Ranson score, BISAP score, SIRS score, and CT severity index score. However, these scoring systems are not designed specifically for pregnant women. Most pregnant women are younger than 55 or 60 years old, and the "age" component of the Ranson score and BISAP score cannot be effectively applied to such patients. In addition, ionizing radiation may pose potential risks to the developing fetus, and radiological diagnostic methods such as CT are generally not used in pregnant women. Therefore, the CT severity index score is difficult to use to assess the severity of such patients with acute pancreatitis. Currently, there is an urgent need to establish a simple and effective prediction system to predict the severity of patients with acute pancreatitis during pregnancy, which is of great significance for reducing the mortality rate of patients and improving the prognosis of patients with acute pancreatitis during pregnancy.

[0003] In order to solve the above problems existing in the prior art, it is of great significance to develop a prediction system that can be widely used in clinical practice to accurately predict the severity of patients with acute pancreatitis during pregnancy. Summary of the Invention

[0004] The purpose of the present invention is to provide a prediction system that can be widely used in clinical practice to accurately predict the severity of patients with acute pancreatitis during pregnancy, which is of great significance.

[0005] The present invention provides a prediction system for predicting the severity of patients with acute pancreatitis during pregnancy. The prediction system is constructed based on the albumin and urea nitrogen levels of patients with acute pancreatitis during pregnancy as prediction indicators.

[0006] Furthermore, the prediction system is a nomogram, which includes lines 1 to 5, which are arranged from top to bottom and are parallel to each other; each line represents a ruler with scale marks on it; The first scale represents the scale of the scores corresponding to the scales on the second and third scales; The second scale represents albumin; The third scale represents urea nitrogen; The fourth scale represents the sum of the scores corresponding to the marks on the second and third scales; The fifth scale represents the probability of patients with acute pancreatitis during pregnancy developing severe acute pancreatitis.

[0007] Furthermore, the scale range of the first ruler is 0 to 100, with 0 at the far left and 100 at the far right; In the second scale, albumin ranges from 15 to 50; In the third scale, urea nitrogen ranges from 0 to 35; The scale range of the fourth ruler is 0 to 160, with 0 at the far left and 160 at the far right; In the fifth scale, the probability of a patient with acute pancreatitis during pregnancy developing severe acute pancreatitis = the sum of the scores on the fourth scale and the corresponding scale value on the fifth scale, ranging from 0.01 to 0.99.

[0008] Furthermore, in the second scale, when the albumin is 50, the corresponding score on the first scale is 0, and when the albumin is 15, the corresponding score on the first scale is 80; In the third scale, when the urea nitrogen is 0, the corresponding score on the first scale is 0, and when the urea nitrogen is 35, the corresponding score on the first scale is 100.

[0009] Furthermore, the unit of albumin is g / L and the unit of urea nitrogen is mg / dL.

[0010] Furthermore, the method for constructing the prediction system includes the following steps: (1) Collect predictive indicators of patients with acute pancreatitis during pregnancy and enter them into the input module; (2) Use the prediction indicators in the input module to build a logistic regression model and draw a nomogram.

[0011] Furthermore, the prediction system shown is as follows Figure 1 shown.

[0012] The present invention also provides a device for predicting the severity of acute pancreatitis in pregnant women, wherein the device comprises the above-mentioned prediction system.

[0013] The present invention also provides use of the above prediction system in preparing a device for predicting the severity of acute pancreatitis in pregnant women.

[0014] For acute pancreatitis during pregnancy, an acute disease with rapid early-stage progression, it is crucial to accurately predict the severity of acute pancreatitis during pregnancy. Compared with existing prediction systems, the prediction system provided by the present invention is more specific and timely.

[0015] In response to the high incidence of severe acute pancreatitis during pregnancy, this paper proposes a system for predicting the severity of acute pancreatitis during pregnancy. Compared with the BISAP and SIRS scores currently used in clinical practice to determine the severity of acute pancreatitis, the nomogram constructed in this paper has a better predictive effect on the severity of acute pancreatitis during pregnancy. It also demonstrates good clinical utility and has a good net benefit for identifying patients with severe acute pancreatitis during pregnancy, helping clinicians maximize their clinical decision-making.

[0016] The prediction system provided by the present invention has a simple construction method, high prediction accuracy and discrimination, and can predict the risk of developing severe acute pancreatitis in patients with acute pancreatitis during pregnancy, which helps to achieve early detection, early diagnosis and early intervention, provides a reference for clinical physicians to make individualized treatment decisions, and effectively improves patient prognosis.

[0017] Obviously, based on the above contents of the present invention, according to common technical knowledge and customary means in this field, without departing from the above basic technical ideas of the present invention, other various forms of modifications, replacements or changes can be made.

[0018] The following further describes the above content of the present invention in detail through specific embodiments in the form of examples. However, this should not be construed as limiting the scope of the above subject matter of the present invention to the following examples. All technologies implemented based on the above content of the present invention fall within the scope of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 A nomogram constructed for predicting the severity of acute pancreatitis during pregnancy is provided by the present invention.

[0020] Figure 2 The area under the receiver operating characteristic curve (AUC) and calibration curve of the prediction system in the development cohort (A, B) are shown. A indicates that the AUC of the prediction system in the development cohort is 0.920, and B indicates that the calibration curve of the prediction system in the development cohort shows good agreement between the predicted severity of acute pancreatitis during pregnancy and the actual severity observed.

[0021] Figure 3 This is the decision curve analysis for constructing the nomogram of the present invention. DETAILED DESCRIPTION

[0022] The principles and features of the present invention are described below with reference to the accompanying drawings. The examples given are only used to explain the present invention and are not used to limit the scope of the present invention.

[0023] Example 1 A prediction system for predicting the probability of severity of acute pancreatitis during pregnancy is established.

[0024] The prediction system of the present invention is a visual nomogram for predicting the probability of patients with acute pancreatitis during pregnancy developing severe acute pancreatitis during pregnancy, and the construction method includes the following steps.

[0025] 1. Patient information (1.1) Inclusion and exclusion criteria Inclusion criteria: Patients with confirmed diagnosis of acute pancreatitis during pregnancy.

[0026] Exclusion criteria: (1) age <18 years, (2) incomplete clinical data, (3) termination of pregnancy within 24 hours after hospitalization, and (4) patients with benign or malignant pancreatic tumors, autoimmune diseases, or chronic diseases (such as chronic obstructive pulmonary disease, chronic heart disease, chronic renal failure, etc.).

[0027] (1.2) Data sources This multicenter retrospective study enrolled 45 patients diagnosed with acute pancreatitis during pregnancy between December 1, 2005, and June 30, 2024, from various tertiary-level A hospitals (the First Affiliated Hospital of Guangxi Medical University, the Second Affiliated Hospital of Guangxi Medical University, and Liuzhou Workers' Hospital) as a development cohort for the development of a clinical prediction model.

[0028] 2. Collect patient clinical data Baseline information collected included age, gestational age, gravidity, parity, and body mass index. Laboratory tests were performed within 24 hours of admission and included white blood cell count, red blood cell count, hemoglobin, platelet count, neutrophil percentage, neutrophil count, lymphocyte percentage, lymphocyte count, monocyte percentage, monocyte count, eosinophil count, hematocrit, total bilirubin, total protein, albumin, globulin, gamma-glutamyl transferase, aspartate aminotransferase, alanine aminotransferase, alkaline phosphatase, prealbumin, cholinesterase, urea nitrogen, creatinine, prothrombin time, fibrinogen, potassium, sodium, chloride, and calcium. The BISAP score and SIRS score were also assessed within 24 hours of admission.

[0029] 3. Construct a visual nomogram (3.1) Univariate and multivariate logistic regression analysis of risk factors Univariate and multivariate logistic regression analyses were used to identify independent risk factors for the severity of acute pancreatitis during pregnancy (Tables 1 and 2). In univariate analysis, gestational age, platelet count, mean platelet volume, albumin, urea nitrogen, and prothrombin time showed statistical significance. After adjustment in multivariate logistic regression analysis, two independent risk factors were identified: albumin (OR 0.72 [95% CI 0.51-0.90]; P = 0.019) and urea nitrogen (OR 1.45 [1.11-2.14]; P = 0.021).

[0030] Table 1. Univariate logistic regression analysis of risk factors for severity of acute pancreatitis during pregnancy in the development cohort. variable OR 95% CI P age 1.02 0.91-1.15 0.689 pregnancy 5.20 1.41-19.18 0.013 Pregnancy 1.68 0.96-2.92 0.069 parity 2.21 0.92-5.31 0.076 Body mass index 1.03 0.85-1.26 0.738 White blood cell count 1.09 0.97-1.21 0.141 Red blood cell count 0.41 0.15-1.09 0.072 Hemoglobin 1.00 0.97-1.02 0.733 Platelet count 0.99 0.98-1.00 0.013 Neutrophil percentage 1.02 0.99-1.05 0.314 Neutrophil count 1.10 0.98-1.24 0.112 Lymphocyte percentage 1.02 0.83-1.26 0.824 Lymphocyte count 0.48 0.15-1.56 0.221 Monocyte percentage 1.20 0.80-1.78 0.377 Monocyte count 0.60 0.07-5.27 0.647 Eosinophil count 0.01 0.00-9.09 0.177 Platelet count 0.00 0.00-19.22 0.178 Mean platelet volume 1.82 1.03-3.22 0.040 Hematocrit 0.01 0.00-402.23 0.415 Mean hematocrit 1.02 0.95-1.10 0.509 mean corpuscular hemoglobin 1.16 0.96-1.39 0.121 Total bilirubin 1.00 0.99-1.01 0.744 Total protein 0.98 0.92-1.04 0.531 albumin 0.79 0.67-0.93 0.006 globulin 1.08 0.98-1.19 0.116 γ-glutamyl transferase 0.99 0.98-1.00 0.300 Aspartate aminotransferase 1.00 1.00-1.01 0.408 Alanine aminotransferase 1.00 0.99-1.01 0.737 Alkaline phosphatase 1.00 1.00-1.01 0.264 Prealbumin 1.00 0.99-1.01 0.832 Cholinesterase 1.00 1.00-1.00 0.086 urea nitrogen 1.33 1.10-1.59 0.002 Creatinine 1.04 1.00-1.07 0.052 Prothrombin time 1.39 1.02-1.88 0.035 Fibrinogen 0.80 0.56-1.16 0.239 potassium 0.72 0.20-2.67 0.627 sodium 1.00 0.91-1.08 0.922 chlorine 1.00 0.93-1.07 0.903 calcium 0.10 0.01-1.38 0.086 Table 2. Multivariate logistic regression analysis of risk factors for severity of acute pancreatitis during pregnancy in the development cohort. variable B OR [95% CI] P pregnancy 1.840 6.29 [0.62, 141.40] 0.156 platelets 0.004 1.00 [0.99, 1.02] 0.659 Mean platelet volume 0.954 2.60 [0.98, 13.33] 0.145 albumin -0.331 0.72 [0.51, 0.90] 0.019 urea nitrogen 0.373 1.45 [1.11, 2.14] 0.021 Prothrombin time 0.111 1.12 [0.62, 2.13] 0.708 (3.2) Draw a visual nomogram Through the stepwise logistic regression model, albumin and urea nitrogen were finally screened out to construct a visual nomogram ( Figure 1 ).

[0031] like Figure 1 As shown, the nomogram contains lines 1 to 5, which are arranged from top to bottom and are parallel to each other. Each line represents a scale with scale marks: The first scale is the scale for the scores corresponding to the scales on the second and third scales, with a score range of 0 to 100, with 0 at the far left and 100 at the far right. The second scale represents albumin, ranging from 15 to 50, in g / L; when the albumin is 50, the corresponding score is 0, and when the albumin is 15, the corresponding score is 80; The third scale represents urea nitrogen, ranging from 0 to 35, in mg / dL; when urea nitrogen is 0, the corresponding score is 0, and when albumin is 35, the corresponding score is 100; The fourth scale represents the sum of the scores corresponding to the marks on the second and third scales; it ranges from 0 to 160, with 0 at the leftmost segment and 160 at the rightmost end. The fifth scale represents the predicted probability of a patient with acute pancreatitis during pregnancy developing severe acute pancreatitis, ranging from 0.01 to 0.99.

[0032] The following experimental examples demonstrate the prediction effect of the prediction system of the present invention.

[0033] Experimental Example 1: Verification of Discrimination and Calibration 1. Experimental methods (1) Verification of model discrimination: The area under the receiver operating characteristic curve (AUC) is used for evaluation. The larger the AUC, the better the discrimination ability of the prediction model.

[0034] (2) Verify the calibration of the model: draw a calibration curve. The degree of closeness between the data points and the dotted straight line in the figure reflects the calibration of the model.

[0035] 2. Experimental results In the development cohort, the AUC of the nomogram was 0.920 ( Figure 2 A), Calibration curve for predicting the severity of acute pancreatitis during pregnancy ( Figure 2 B) shows good agreement with the actual severity.

[0036] The above experimental results show that the prediction model established by the present invention has excellent discrimination and calibration.

[0037] Experimental Example 2 Comparison of the Prediction System of the Present Invention with the Conventional Clinical Prognosis Scoring System 1. Experimental methods The prediction system of Example 1 of the present invention was compared with other clinical scoring systems (including BISAP and SIRS scores) in terms of AUC, sensitivity, specificity, positive likelihood ratio (PLR), negative likelihood ratio (NLR), positive predictive value (PPV) and positive predictive value (NPV).

[0038] The clinical utility of the prediction system of Example 1 of the present invention and conventional clinical scoring systems (BISAP and SIRS scores) were compared, as well as the net benefit of clinical use in identifying SAP patients.

[0039] 2. Experimental results The PLR ​​stands for Positive Likelihood Ratio, which is the ratio of the True Positive Rate (TPR) to the False Positive Rate (FPR) of a screening test. It indicates how likely a screening test is to correctly identify a positive result as multiple times the likelihood of an incorrectly identified positive result. The larger the ratio, the greater the probability that a positive test result is a true positive. The NLR stands for Negative Likelihood Ratio, which is the ratio of the False Negative Rate (FNR) to the True Negative Rate (NTR) of a screening test. It indicates how likely a falsely identified negative result is to incorrectly identify a negative result as multiple times the likelihood of a correct negative result. The smaller the ratio, the greater the probability that a negative test result is a true negative. A PLR > 10 or an NLR < 0.1 essentially confirms or excludes the diagnosis.

[0040] In the development cohort, 40% (18 / 45) of patients with acute pancreatitis during pregnancy progressed to moderately severe or severe acute pancreatitis.

[0041] In the development cohort, the nomogram of the present invention had the best prediction effect on the severity of acute pancreatitis in pregnant patients (AUC 0.920 [0.830-1.000], PLR 7.407), followed by the BISAP score (AUC 0.875 [0.771-0.979], PLR 6.667), and finally the SIRS score (AUC 0.728 [0.585-0.872], PLR 2.357).

[0042] Additionally, the development queue ( Figure 3 The nomogram of the present invention demonstrated better or equal clinical utility compared to other prognostic scoring systems and had a good net benefit in clinically identifying the severity of acute pancreatitis in pregnant patients. This suggests that the nomogram of the present invention can help clinicians maximize their benefit when making clinical decisions, as it demonstrates greater benefit than the extremes of diagnosing severe acute pancreatitis in all patients with acute pancreatitis during pregnancy or not diagnosing severe acute pancreatitis.

[0043] The above results show that compared with the conventional scoring systems currently used clinically to determine the severity of acute pancreatitis during pregnancy (including BISAP and SIRS scores), the nomogram constructed by the present invention has a better predictive effect on the probability of patients with acute pancreatitis during pregnancy developing severe acute pancreatitis; at the same time, it shows good clinical utility and has a good clinical net benefit for identifying the severity of patients with acute pancreatitis during pregnancy, which can help clinicians obtain maximum benefits when making clinical decisions.

[0044] In summary, the present invention provides a prediction system for predicting the severity of patients with acute pancreatitis during pregnancy that can be promoted and applied clinically. The prediction system has a simple construction method, high prediction accuracy and discrimination, and can accurately determine the probability of patients with acute pancreatitis during pregnancy developing severe acute pancreatitis, helping clinicians to obtain maximum benefits when making clinical decisions, helping to guide physicians to make individualized treatment decisions, and improving patient survival rates.

Claims

1. A prediction system for predicting the severity of acute pancreatitis during pregnancy, characterized by: The prediction system is constructed using albumin and urea nitrogen levels of patients with acute pancreatitis during pregnancy as prediction indicators.

2. The prediction system according to claim 1, wherein: The prediction system is a nomogram, which includes lines 1 to 5, which are arranged in sequence from top to bottom and are parallel to each other; each line represents a ruler with scale marks on it; The first scale represents the scale of the scores corresponding to the scales on the second and third scales; The second scale represents albumin; The third scale represents urea nitrogen; The fourth scale represents the sum of the scores corresponding to the marks on the second and third scales; The fifth scale represents the probability of patients with acute pancreatitis during pregnancy developing severe acute pancreatitis.

3. The prediction system according to claim 2, characterized in that: The scale range of the first ruler is 0 to 100, with 0 at the far left and 100 at the far right; In the second scale, albumin ranges from 15 to 50; In the third scale, urea nitrogen ranges from 0 to 35; The scale range of the fourth ruler is 0 to 160, with 0 at the far left and 160 at the far right; In the fifth scale, the probability of a patient with acute pancreatitis during pregnancy developing severe acute pancreatitis = the sum of the scores on the fourth scale and the corresponding scale value on the fifth scale, ranging from 0.01 to 0.

99.

4. The prediction system according to claim 3, characterized in that: In the second scale, when the albumin level is 50, the corresponding score on the first scale is 0, and when the albumin level is 15, the corresponding score on the first scale is 80; In the third scale, when the urea nitrogen is 0, the corresponding score on the first scale is 0, and when the urea nitrogen is 35, the corresponding score on the first scale is 100.

5. The prediction system according to claim 4, characterized in that: The unit of albumin is g / L, and the unit of urea nitrogen is mg / dL.

6. The prediction system according to claim 1, wherein: The method for constructing the prediction system comprises the following steps: (1) Collect predictive indicators of patients with acute pancreatitis during pregnancy and enter them into the input module; (2) Use the prediction indicators in the input module to build a logistic regression model and draw a nomogram.

7. The prediction system according to any one of claims 1 to 6, characterized in that: The prediction system is shown in Figure 1.

8. A device for predicting the severity of acute pancreatitis during pregnancy, characterized by: The device comprises the prediction system according to any one of claims 1 to 7.

9. Use of the prediction system according to any one of claims 1 to 7 in the preparation of a device for predicting the severity of acute pancreatitis in pregnant women.

Images