Risk prediction model for hypoxic hepatitis after severe burn, construction method and storage medium

Abstract

The invention relates to a risk prediction model for hypoxic hepatitis after severe burn, a construction method and a storage medium. The construction method comprises the following steps: collecting clinical characteristic data of hypoxic hepatitis occurring and not occurring after serious burn; analyzing and screening the preprocessed clinical characteristic data with the p value less than 0.05 and whether the hypoxic hepatitis occurs or not by using a regression model, and screening the clinical characteristic data related to the hypoxic hepatitis after serious burn; and constructing a risk prediction model based on the screened clinical feature data and laboratory data. The invention also provides a risk prediction model constructed by the construction method. The invention further provides a storage medium. Based on the clinical basic data and disease related indexes of the patient, the risk factors that the severe burn patient may have hypoxic hepatitis are identified, so that the probability of hypoxic hepatitis occurrence is predicted conveniently, quickly and accurately in advance, and doctors are helped to take corresponding prevention and treatment measures for the patient.

Description

Technical Field

[0001] The present invention relates to the field of medical diagnosis technology, and in particular to a risk prediction model, a construction method and a storage medium for hypoxic hepatitis after severe burns. Background Art

[0002] Burns are a very common type of trauma in daily life, which poses a great threat to human life and health. Burns may not only cause long-term physical and mental problems, but also a large number of patients lose their precious lives due to burns every year around the world. The classification of burns mainly includes the depth of the burn and the area of ​​the burn. The depth of burns ranges from first to fourth degree, while the burn area is divided into mild and severe. Mild burns are characterized by a burn area less than 10% of the total body surface area (TBSA), mainly manifested as surface burns. In general, patients with a total surface area burn of >20% or full-thickness burns of >10% are defined as severe burns.

[0003] Although the prognosis of patients with severe burns has been greatly improved with the advancement of medical technology, more than 300,000 people still die from severe burns worldwide. Patients with severe burns often develop sepsis with (multiple organ dysfunction syndrome) MODS. In fact, MODS is the main cause of death within 24 hours of severe burn injury. The liver is the most important organ for biochemical synthesis and decomposition. Liver damage after burns has been confirmed. Liver necrosis and liver dysfunction after burns were reported in the late 1930s. Subsequently, many studies have shown that liver dysfunction, liver volume enlargement, and fatty infiltration are common in burn patients and are related to the total body surface area (TBSA) burned. Although the treatment of burn patients has improved significantly in recent decades, severe burns are still fatal, and the incidence of hypoxic hepatitis in patients with severe burns is still at a relatively high level.

[0004] Among them, hypoxic hepatitis (HH) is a complication of the underlying disease and an acute liver injury that mainly occurs in patients with heart failure, respiratory failure, septic or toxic shock and other underlying diseases. It has a high incidence and poor prognosis in critically ill patients.

[0005] At present, the incidence of hypoxic hepatitis in patients with severe burns is often judged based on observing the patient's clinical manifestations, which can easily miss the best time to prevent hypoxic hepatitis. There is no prediction method in the prior art on whether patients with severe burns will develop hypoxic hepatitis, which makes it impossible to prevent and treat it in time. Therefore, timely and accurate prediction of whether patients with severe burns will develop hypoxic hepatitis in the future is crucial to assessing the patient's clinical prognosis and guiding individualized treatment. Summary of the invention

[0006] In view of this, the purpose of the present invention is to provide a risk prediction model, construction method and storage medium for hypoxic hepatitis after severe burns, so as to identify the risk factors for hypoxic hepatitis in patients with severe burns based on the patient's basic clinical data and disease-related indicators, and use these factors to establish a fully verified risk prediction model to conveniently, quickly and accurately predict the probability of hypoxic hepatitis in patients in advance, thereby helping doctors take corresponding preventive and treatment measures for patients.

[0007] In order to achieve the above object, the technical solution adopted by the present invention is as follows:

[0008] A method for constructing a risk prediction model for hypoxic hepatitis after severe burns, comprising the following steps:

[0009] S1. Data collection and preprocessing: clinical characteristic data of patients with and without hypoxic hepatitis after severe burns were collected and preprocessed;

[0010] S2. Feature data screening: The preprocessed clinical feature data were divided into a training set and a validation set. The clinical feature data of the training set with a p-value less than 0.05 and whether hypoxic hepatitis occurred were analyzed and screened using the LASSO regression model to screen out the clinical feature data of hypoxic hepatitis after severe burns.

[0011] S3. Model construction: Based on the screened clinical characteristic data related to hypoxic hepatitis after severe burns, a risk prediction model for hypoxic hepatitis after severe burns was constructed.

[0012] According to the above technical means, by collecting clinical characteristic data of patients with and without hypoxic hepatitis after severe burns, the breadth and diversity of data sources are ensured, which helps to improve the accuracy and reliability of the prediction model; in the data preprocessing stage, the collected clinical characteristic data are cleaned and standardized to improve the data quality, which can effectively eliminate noise and outliers in the data and provide a higher quality data basis for subsequent analysis; the LASSO regression model is used for feature data screening, which can effectively identify clinical characteristics related to the occurrence of hypoxic hepatitis, and at the same time, the statistical significance of the characteristics is ensured by the screening standard of p value less than 0.05; the clinical characteristic data includes the patient's clinical manifestations and laboratory test indicators, making the constructed prediction model more comprehensive and integrated, and improving the accuracy of the prediction; the risk prediction model constructed based on the screened clinical characteristic data can provide important reference information for clinicians, helping doctors to identify the risk of hypoxic hepatitis after severe burns earlier, so as to take timely prevention and treatment measures and improve the prognosis of patients.

[0013] Preferably, the clinical characteristic data include gender, age, cause of burns, past medical history, smoking history, drinking history, burn area, third-degree burn area, BMI, burn site, number of liver injuries before HH, length of hospitalization, length of ICU stay, mortality rate, AST admission value, ALT admission value, GGT admission value, ALP, direct bilirubin, indirect bilirubin, LDH, albumin, prealbumin, fibrinogen, admission value of blood creatinine, maximum value of blood creatinine, maximum value of AST and maximum value of GGT.

[0014] Preferably, the clinical characteristic data of hypoxic hepatitis after severe burns include the patient's electrical burns, the patient's smoking history, the patient's albumin value upon admission, the patient's total burn area, the patient's aspartate aminotransferase (AST) upon admission, and the number of liver injuries before the patient developed hypoxic hepatitis.

[0015] Preferably, the risk prediction model is a nomogram model.

[0016] Preferably, in the nomogram model:

[0017] The first column is the score scale, ranging from 0 to 100; the second column is the patient's electric burns, with 1 point for patients with electric burns and 0 point for patients without electric burns; the third column is the patient's smoking history, with 1 point for patients with a smoking history and 0 point for patients without a smoking history; the fourth column is the patient's albumin at admission, ranging from 0 to 0.4; the fifth column is the patient's total burn area, ranging from 0 to 100; the sixth column is the patient's aspartate aminotransferase (AST) value at admission, ranging from 0 to 1800; the seventh column is the number of liver injuries before the patient developed hypoxic hepatitis, ranging from 0 to 2; the eighth column is the total score, ranging from 0 to 180; the ninth column is the probability of the patient developing hypoxic hepatitis, ranging from 0.01 to 0.99.

[0018] Among them, in the nomogram, the second to seventh rows are related factors, and different factor states correspond to different scale scores; the total score of the eighth row is the sum of the scores of each factor, and there is a corresponding relationship between the total scores of the eighth and ninth rows. According to different scores, they are projected to corresponding positions, which are the corresponding probabilities of hypoxic hepatitis after severe burns.

[0019] Preferably, the risk prediction model also includes a risk value formula:

[0020]

[0021] In formula (I), X1 represents the patient's electric burns, the patient has electric burns corresponding to a score of 1 point, and the patient has no electric burns corresponding to a score of 0 point; X2 represents the patient's smoking history, the patient has a smoking history corresponding to a score of 1 point, and the patient has no smoking history corresponding to a score of 0 point; X3 represents the patient's albumin at admission; X4 represents the patient's total burn area; X5 represents the patient's aspartate aminotransferase (AST) value at admission; X6 represents the number of liver injuries before the patient develops hypoxic hepatitis; P represents the probability of the patient developing hypoxic hepatitis.

[0022] Preferably, the maximum AUROC value of the nomogram model is 0.938.

[0023] Preferably, the p-value is obtained by a t-test or a chi-square test.

[0024] Preferably, in S1, the clinical characteristic data is randomly divided into a 70% training set and a 30% test set; the model is trained by the training data set to obtain a death risk prediction model;

[0025] The death risk prediction model was validated using the test set.

[0026] The present invention also provides a risk prediction model for hypoxic hepatitis after severe burns constructed by the construction method of the present invention.

[0027] Preferably, the risk prediction model for hypoxic hepatitis after severe burns comprises:

[0028] The data collection and preprocessing module is used to collect clinical characteristic data of patients with and without hypoxic hepatitis after severe burns, and to preprocess the clinical characteristic data;

[0029] The feature data screening module is used to divide the pre-processed clinical feature data into a training set and a validation set, and use the LASSO regression model to analyze and screen the clinical feature data of the training set with a p value less than 0.05 and whether hypoxic hepatitis occurs, and screen out the clinical feature data of hypoxic hepatitis after severe burns;

[0030] The prediction model building module is used to build a risk prediction model for hypoxic hepatitis after severe burns based on the screened clinical characteristic data related to hypoxic hepatitis after severe burns.

[0031] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the construction method described in the present invention are implemented.

[0032] Beneficial effects of the present invention:

[0033] The method for constructing a risk prediction model for hypoxic hepatitis after severe burns of the present invention ensures the breadth and diversity of data sources by collecting clinical feature data of patients with and without hypoxic hepatitis after severe burns, which helps to improve the accuracy and reliability of the prediction model; in the data preprocessing stage, the collected clinical feature data are cleaned and standardized to improve the data quality, which can effectively eliminate noise and outliers in the data and provide a higher quality data basis for subsequent analysis; the LASSO regression model is used to screen feature data, which can effectively identify clinical features related to the occurrence of hypoxic hepatitis, and at the same time, the statistical significance of the features is ensured by the screening standard of p value less than 0.05; the combination of clinical manifestations and experimental detection indicators makes the constructed prediction model more comprehensive and integrated, and improves the accuracy of the prediction; the risk prediction model constructed based on the screened indicators can provide important reference information for clinicians, help doctors identify the risk of hypoxic hepatitis after severe burns earlier, so as to take timely prevention and treatment measures and improve the prognosis of patients, and has promotion and application value in the field of medical diagnosis technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 Flowchart of data collection and preprocessing for patients with severe burns;

[0035] Figure 2 A nomogram model for the risk prediction of hypoxic hepatitis after severe burns;

[0036] Figure 3 The training set subject cohort operating characteristic curve for the logistic regression model;

[0037] Figure 4 Receiver operating characteristic curve for the test set cohort of the logistic regression model;

[0038] Figure 5 This is the result diagram of the decision curve analysis of the training set cohort of the nomogram model;

[0039] Figure 6 This is the result diagram of the test set cohort decision curve analysis of the nomogram model;

[0040] Figure 7 This is a graph showing the results of the calibration curve analysis of the training set cohort of the nomogram model;

[0041] Figure 8 Figure 3. Results of calibration curve analysis of the test set cohort for the nomogram model. DETAILED DESCRIPTION

[0042] The following will describe the embodiments of the present invention with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention, not for limiting the scope of protection of the present invention.

[0043] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and thus the drawings only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0044] The present invention intends to disclose a risk prediction model, construction method and storage medium for hypoxic hepatitis after severe burns, so as to identify the risk factors for hypoxic hepatitis in patients with severe burns based on the patient's basic clinical data and disease-related indicators, and use these factors to establish a fully verified risk prediction model to conveniently, quickly and accurately predict the probability of hypoxic hepatitis in patients in advance, thereby helping doctors take corresponding preventive and treatment measures for patients.

[0045] Among them, Figure 1 As shown, the method for constructing a risk prediction model for hypoxic hepatitis after severe burns includes the following steps:

[0046] S1. Data collection: clinical characteristic data of patients with and without hypoxic hepatitis after severe burns were collected and preprocessed;

[0047] S2. Feature data screening: The preprocessed clinical feature data were divided into a training set and a validation set. The clinical feature data of the training set with a p value of less than 0.05 in the t-test or chi-square test and whether hypoxic hepatitis occurred were analyzed and screened using the LASSO regression model to screen out the clinical feature data of hypoxic hepatitis after severe burns;

[0048] S3. Model construction: Based on the screened clinical characteristic data of hypoxic hepatitis after severe burns, a risk prediction model for hypoxic hepatitis after severe burns was constructed.

[0049] Among them, hypoxic hepatitis (HH) is defined as a syndrome characterized by a rapid and transient increase in alanine aminotransferase (ALT) or aspartate aminotransferase (AST) to more than 10 times the upper limit of normal in the context of cardiac, circulatory, or respiratory failure. It is characterized by a primary pattern of hepatocellular injury without evidence of cholestasis.

[0050] In some embodiments, the clinical characteristic data include gender, age, cause of burns, past medical history, smoking history, drinking history, burn area, BMI, burn site, number of liver injuries before HH, length of admission, length of ICU stay, mortality, AST admission value, ALT admission value, GGT admission value, ALP, direct bilirubin, indirect bilirubin, LDH, albumin, prealbumin, fibrinogen, blood creatinine admission value, AST maximum value, GGT maximum value and blood creatinine maximum value.

[0051] In some embodiments, the clinical characteristic data of hypoxic hepatitis after severe burns include the patient's electrical burns, the patient's smoking history, the patient's albumin value upon admission, the patient's total burn area, the patient's aspartate aminotransferase (AST) upon admission, and the number of liver injuries before the patient developed hypoxic hepatitis.

[0052] In some embodiments, the mortality risk prediction model is a nomogram model.

[0053] Exemplarily, in S1, data collection and preprocessing include:

[0054] Data of 742 patients who were consecutively admitted to the Burn Department of Southwest Hospital from January 2017 to December 2022 were collected and preprocessed. The data of 88 patients with missing information and 81 patients with TBSA ≤ 20% were removed, resulting in 573 patients with severe burns. Among them, 51 patients developed hypoxic hepatitis (HH). Logistic regression analysis was used to screen 26 potential risk factors for HH in patients with severe burns. The results showed that electrical burns (OR = 3.276, p = 0.031), TBSA (OR = 1.042, p < 0.001), smoking history (OR = 3.199, p = 0.008), and admission AST value (OR = 1.008, p < 0.001) had a significant effect on HH after severe burns (see Table 3). Consistent with the above analysis, LASSO regression analysis also found that these indicators were positively correlated with the occurrence of HH.

[0055] Among them, during the pretreatment process, the exclusion criteria were: patients with outpatient or severely incomplete medical records; patients without liver function tests in the BICU; patients with BICU ≤ 48 hours of hospitalization; patients admitted more than 7 days after burns; patients with abnormal ALT / AST levels at BICU admission.

[0056] Exemplarily, S2, feature data screening, includes:

[0057] A total of 573 patients with severe burns were divided into two groups: HH group (N = 51) and non-HH group (N = 522) (Table 2). There were more males in HH patients (16.0:1 vs. 2.81:1, p = 0.001). HH patients experienced fewer scalds (7.84% vs. 24.90%, p = 0.006) and more electrical burns (41.18% vs. 10.92%, p < 0.001). The severity of burns was significantly higher in the HH group, including total burn area [45 (30, 61) vs. 35 (25, 52), p = 0.006], full-thickness burn area [27 (14, 40) vs. 8 (0, 22), p < 0.001], ABSI [10 (8, 11) vs. 88, 7, 10), p = 0.011), burn index [36 (24, 46) vs. 18.75 (9.5, 31.6), p < 0.001], and Baux score [101 (80, 121) vs. 89 (74, 110), p = 0.042]. It is worth noting that the proportion of heart disease in HH patients was significantly higher than that in the non-HH group (7.84% vs. 2.11%, p = 0.036), and the number of pre-HH liver lesions was also significantly different between the two groups (p < 0.001) (see Table 1).

[0058] The results of the analysis showed that the mortality rate (37.25% vs. 14.37%, p < 0.001) and ICU length of stay [0 (0, 37) vs. 0 (0, 37), p = 0.024] were also higher in the HH group. In the laboratory data, most indicators showed significant differences between the HH group and the non-HH group, including admission and the mean values ​​of ALT, AST, GGT, albumin, prealbumin, direct bilirubin, and indirect bilirubin. These indicators will be used together with the baseline data to determine the final risk factors by Lasso regression in subsequent analyses (see Table 2).

[0059] Table 1. Clinical baseline data of HH patients and non-HH patients (* represents the use of Fisher test, other categorical variables use chi-square test, and continuous variables use non-parametric test)

[0060]

[0061]

[0062] Table 2. Laboratory test indicators in clinical characteristics data of HH patients and non-HH patients

[0063]

[0064] Table 3. Multivariate logistic regression analysis of risk factors for hypoxic hepatitis in patients with severe burns

[0065]

[0066]

[0067] Exemplarily, S3, model construction, including: based on the above-screened clinical feature data related to hypoxic hepatitis after severe burns, construct a nomogram of the risk prediction model for hypoxic hepatitis after severe burns, such as Figure 2 shown.

[0068] Among them, in the nomogram model:

[0069] The first column is the score scale, ranging from 0 to 100; the second column is the patient's electric burns, with 1 point for patients with electric burns and 0 point for patients without electric burns; the third column is the patient's smoking history, with 1 point for patients with a smoking history and 0 point for patients without a smoking history; the fourth column is the patient's albumin at admission, ranging from 0 to 0.4; the fifth column is the patient's total burn area, ranging from 0 to 100; the sixth column is the patient's aspartate aminotransferase (AST) value at admission, ranging from 0 to 1800; the seventh column is the number of liver injuries before the patient developed hypoxic hepatitis, ranging from 0 to 2; the eighth column is the total score, ranging from 0 to 180; the ninth column is the probability of the patient developing hypoxic hepatitis, ranging from 0.01 to 0.99.

[0070] Among them, in the nomogram, the second to seventh rows are related factors, and different factor states correspond to different scale scores; the total score of the eighth row is the sum of the scores of each factor, and there is a corresponding relationship between the total score of the ninth row and the eighth row. According to different scores, they are projected to corresponding positions, which are the corresponding probabilities of hypoxic hepatitis after severe burns.

[0071] The maximum AUROC value of the nomogram model was 0.938 (95% CI 0.795-0.945), indicating a good fit.

[0072] In some embodiments, the risk prediction model further includes a risk value formula:

[0073]

[0074] In formula (I), X1 represents the patient's electric burns, the patient has electric burns corresponding to a score of 1 point, and the patient has no electric burns corresponding to a score of 0 point; X2 represents the patient's smoking history, the patient has a smoking history corresponding to a score of 1 point, and the patient has no smoking history corresponding to a score of 0 point; X3 represents the patient's albumin at admission; X4 represents the patient's total burn area; X5 represents the aspartate aminotransferase (AST) value at admission; X6 represents the number of liver injuries before the patient develops hypoxic hepatitis; P represents the probability of the patient developing hypoxic hepatitis.

[0075] Using the internal validation method, the clinical characteristics data of the above severe burn patients were randomly divided into a training set (70%) and a test set (30%). The model was then trained with the training set and validated with the test set. Figures 3 to 8 shown.

[0076] in, Figure 3 The training set subject cohort operating characteristic curve for the logistic regression model; Figure 4 The figure is the receiver operating characteristic curve of the test set cohort of the logistic regression model. The AUC of the training set and test set of the model are 0.938 and 0.859 respectively, and the prediction performance is good. Figure 5 Results of calibration curve analysis for the training set cohort of the nomogram model; Figure 6 This is the result of the calibration curve analysis of the test set cohort of the nomogram model. Calibration is an indicator of the goodness of fit of the model, which measures the consistency between the actual probability of the outcome and the probability predicted by the model, and reflects the accuracy of the model in predicting absolute risk. The calibration curve in the result graph of this model is close to the ideal line, indicating that the predicted probability of the model matches the actual probability of occurrence. Figure 7 The results of decision curve analysis for the training set cohort of the nomogram model; Figure 8 This is the result of the test set cohort decision curve analysis of the nomogram model. In the result graph of this model, the overall benefit value of the prediction model in the range of 0 to 1 is basically higher than the all line and the none line at the corresponding threshold probability, indicating that the model has practical value.

[0077] In some embodiments, a mortality risk prediction model for severe burns combined with hypoxic hepatitis constructed by the construction method in any of the above embodiments is also provided, comprising:

[0078] The data collection and preprocessing module is used to collect clinical characteristic data of patients with and without hypoxic hepatitis after severe burns, and to preprocess the clinical characteristic data;

[0079] The feature data screening module is used to divide the pre-processed clinical feature data into a training set and a validation set, and use the LASSO regression model to analyze and screen the clinical feature data of the training set with a p value less than 0.05 and whether hypoxic hepatitis occurs, and screen out the clinical feature data of hypoxic hepatitis after severe burns;

[0080] The prediction model building module is used to build a risk prediction model for hypoxic hepatitis after severe burns based on the screened clinical characteristic data related to hypoxic hepatitis after severe burns.

[0081] In some embodiments, a computer-readable storage medium is also provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the construction method in any of the above embodiments are implemented.

[0082] In summary, the risk prediction model for hypoxic hepatitis after severe burns of the present invention is to comprehensively evaluate the patient's clinical characteristic data (including clinical manifestations and laboratory test indicators) to reduce misjudgment caused by one-sided information. When the patient has not yet received treatment, a nomogram model based on clinical characteristic data can be used to assist severe burn patients in predicting whether hypoxic hepatitis will occur. The model of the present invention is simple, intuitive, and easy to promote and apply. It can effectively allow clinicians to conduct accurate individualized assessments of severe burn patients before receiving treatment, bringing better survival benefits to patients. It has important value for the effective application of prevention of severe burns combined with hypoxic hepatitis, and provides personalized and professional health management plans for different stratifications. It has promotion and application value in the field of medical diagnostic technology.

[0083] The above embodiments are only preferred embodiments for fully illustrating the present invention, and the protection scope of the present invention is not limited thereto. Any equivalent substitution or change made by a person skilled in the art based on the present invention is within the protection scope of the present invention.

Claims

1. A method for constructing a risk prediction model for hypoxic hepatitis after severe burns, characterized in that: The following steps are involved: S1. Data collection and preprocessing: clinical characteristic data of patients with and without hypoxic hepatitis after severe burns were collected and preprocessed; S2. Feature data screening: The preprocessed clinical feature data were divided into a training set and a validation set. The LASSO regression model was used to analyze and screen the clinical feature data with a p value less than 0.05 and whether hypoxic hepatitis occurred, and the clinical feature data of hypoxic hepatitis after severe burns were screened out; S3. Model construction: Based on the screened clinical characteristic data related to hypoxic hepatitis after severe burns, a risk prediction model for hypoxic hepatitis after severe burns was constructed.

2. The method for constructing a risk prediction model for hypoxic hepatitis after severe burns according to claim 1, characterized in that: The clinical characteristic data included sex, age, cause of burns, past medical history, smoking history, drinking history, total burn area, third-degree burn area, BMI, burn site, number of liver injuries before HH, hospitalization duration, ICU stay duration, mortality, AST, ALT, GGT, ALP, direct bilirubin, indirect bilirubin, LDH, albumin, prealbumin, fibrinogen, admission values ​​of serum creatinine, and maximum value of serum creatinine; And / or, the screened clinical characteristic indicators of hypoxic hepatitis after severe burns include the patient's electrical burns, the patient's smoking history, the patient's albumin value upon admission, the patient's total burn area, the patient's aspartate aminotransferase (AST) upon admission, and the number of liver injuries before the patient developed hypoxic hepatitis.

3. The method for constructing a risk prediction model for hypoxic hepatitis after severe burns according to claim 2, characterized in that: The risk prediction model is a nomogram model.

4. The method for constructing a risk prediction model for hypoxic hepatitis after severe burns according to claim 3, characterized in that: In the nomogram model: The first column is the score scale, ranging from 0 to 100; the second column is the patient's electric burns, with 1 point for patients with electric burns and 0 point for patients without electric burns; the third column is the patient's smoking history, with 1 point for patients with a smoking history and 0 point for patients without a smoking history; the fourth column is the patient's albumin at admission, ranging from 0 to 0.4; the fifth column is the patient's total burn area, ranging from 20 to 100; the sixth column is the patient's aspartate aminotransferase (AST) value at admission, ranging from 0 to 1800; the seventh column is the number of liver injuries before the patient developed hypoxic hepatitis, ranging from 0 to 2; the eighth column is the total score, ranging from 0 to 180; the ninth column is the probability of the patient developing hypoxic hepatitis, ranging from 0.01 to 0.

99.

5. The method for constructing a risk prediction model for hypoxic hepatitis after severe burns according to claim 3, characterized in that: The risk prediction model also includes a risk value formula: In formula (I), X1 represents the patient's electric burns, the patient has electric burns corresponding to a score of 1 point, and the patient has no electric burns corresponding to a score of 0 point; X2 represents the patient's smoking history, the patient has a smoking history corresponding to a score of 1 point, and the patient has no smoking history corresponding to a score of 0 point; X3 represents the patient's albumin at admission; X4 represents the patient's total burn area; X5 represents the patient's aspartate aminotransferase (AST) value at admission; X6 represents the number of liver injuries before the patient develops hypoxic hepatitis; P represents the probability of the patient developing hypoxic hepatitis.

6. The method for constructing a risk prediction model for hypoxic hepatitis after severe burns according to claim 3, characterized in that: The maximum AUROC value of the nomogram model was 0.

938.

7. The method for constructing a risk prediction model for hypoxic hepatitis after severe burns according to claim 1, characterized in that: The p value is obtained by t test or chi-square test; And / or, in S1, the clinical characteristic data is randomly divided into a 70% training set and a 30% test set; the model is trained by the training data set to obtain a death risk prediction model; The death risk prediction model was validated using the test set.

8. A risk prediction model for hypoxic hepatitis after severe burns constructed by the construction method according to any one of claims 1 to 7.

9. The risk prediction model for hypoxic hepatitis after severe burns according to claim 8, characterized in that: include: The data collection and preprocessing module is used to collect clinical characteristic data of patients with and without hypoxic hepatitis after severe burns, and preprocess the clinical characteristic data; The feature data screening module is used to divide the pre-processed clinical feature data into a training set and a validation set, and use the LASSO regression model to analyze and screen the clinical feature data of the training set with a p value less than 0.05 and whether hypoxic hepatitis occurs, and screen out the clinical feature data of hypoxic hepatitis after severe burns; The prediction model building module is used to build a risk prediction model for hypoxic hepatitis after severe burns based on the screened clinical characteristic data related to hypoxic hepatitis after severe burns.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the construction method according to any one of claims 1 to 7 are implemented.

Images