Construction method of sepsis cardiomyopathy diagnosis model and diagnosis system

Abstract

The invention discloses a construction method of a sepsis cardiomyopathy diagnosis model and a diagnosis system, and relates to the technical field of biomedicine, and the method comprises the following steps: carrying out multi-mode ultrasonic data dynamic collection and clinical data collection on a sepsis patient; according to the multi-mode ultrasonic data, evaluating the overall and local diastolic and contraction functions of the left ventricle and the right ventricle of the heart of the patient with sepsis cardiomyopathy, and performing preliminary diagnosis of sepsis cardiomyopathy in combination with clinical data; the method comprises the following steps: dividing multi-modal ultrasonic data of a sepsis patient into a training set and a verification set by using an Rcaret packet, and carrying out minimum absolute contraction and LASSO regression analysis on the training set to determine a preliminary prediction factor; carrying out logistic regression analysis on the preliminary prediction factor, and determining an independent prediction factor; the independent predictive factors are translated in nomoscore through an rms packet to obtain a column diagram, the independent predictive factors are visually presented according to the weights of the independent predictive factors, and the probability of occurrence of sepsis cardiomyopathy is measured. According to the invention, comprehensive and dynamic quantitative evaluation of the cardiac function of the patient is realized based on the multi-modal ultrasonic parameters.

Description

Technical Field

[0001] The present invention relates to the field of biomedical technology, and in particular to a method for constructing a septic cardiomyopathy diagnosis model and a diagnosis system. Background Art

[0002] Sepsis is a life-threatening organ dysfunction caused by the body's dysregulated response to infection and is the leading cause of death in hospitalized critically ill patients. According to statistics, approximately 48.9 million people worldwide suffered from sepsis in 2017, of which 11 million died, accounting for 20% of global deaths. The heart is the main organ affected by sepsis. The cardiac dysfunction induced by sepsis is called sepsis-induced cardiomyopathy (SIC), which is characterized by overall but reversible dysfunction of the heart. 10%-70% of sepsis patients will develop SIC, with a mortality rate of up to 70%-90%, which seriously worsens the prognosis of sepsis. SIC has obvious heterogeneity, diverse clinical manifestations, unclear pathogenesis, difficulty in early diagnosis, and lack of specific treatment methods. It is one of the hot spots in critical care medicine research.

[0003] Currently, there is no unified diagnostic standard for SIC, but current studies have confirmed that SIC has the following basic characteristics: (1) acute and reversible, with cardiac function gradually returning to normal 7 to 10 days after onset; (2) global and biventricular systolic and / or diastolic dysfunction, accompanied by decreased contractility; (3) left ventricular dilatation; (4) poor response to fluid resuscitation and catecholamines; and (5) exclusion of myocardial ischemia caused by acute coronary artery stenosis.

[0004] In the 1980s, Parker et al. used ventriculography to study cardiac function and initially recognized septic cardiomyopathy, which is left ventricular dilatation with systolic dysfunction, which recovers in 7 to 10 days. This study has aroused the attention of many scholars to septic cardiomyopathy, and various methods such as echocardiography have been used to observe the changes in left ventricular contraction, left ventricular relaxation and right ventricular function in patients with sepsis. With the deepening of research, people have gradually realized that septic cardiomyopathy has a variety of clinical phenotypes, which can be manifested as left ventricular systolic dysfunction (LVSDF), left ventricular diastolic dysfunction (LVDDF), right ventricular dysfunction (RVDF), diffuse ventricular dysfunction and (or) mixed ventricular dysfunction (Mixed). The heterogeneity of clinical manifestations of septic cardiomyopathy and the different types of hemodynamic changes and different clinical outcomes caused by it have made researchers realize the correct early identification of different subtypes of septic cardiomyopathy. It is crucial to accurately treat septic cardiomyopathy.

[0005] Echocardiography is a basic means of evaluating cardiac structure and function. In the early days, a decrease in left ventricular ejection fraction (LVEF) was used as a standard for diagnosing SIC. However, LVEF reflects the result of the superposition of left ventricular contraction and left ventricular afterload coupling, and is significantly affected by afterload. Patients with septic shock often have decreased peripheral vascular resistance. Even if the intrinsic contractility of the left ventricular myocardium has decreased, a normal LVEF can be shown due to the simultaneous decrease in afterload. At the same time, the distribution of LVEF in patients with sepsis presents a "u"-shaped nonlinear distribution. Even patients with a high dynamic state, that is, LVEF>70%, have a high short-term mortality rate. Therefore, LVEF as a single diagnostic standard for SIC may lead to delayed or missed diagnosis of SIC. This indicates that LVEF is not the best ultrasound indicator for diagnosing septic cardiomyopathy. Therefore, indicators that reflect the intrinsic contractility of the myocardium, which are not affected by the preload and afterload of the heart, are more likely to reflect the functional state of the myocardium in sepsis. Tissue Doppler measurement of the peak systolic velocity (S') of the mitral annulus at the septum or lateral wall of the mitral annulus can be used to assess global left ventricular function, which is less dependent on loading conditions than LVEF. However, a meta-analysis demonstrated no difference in the S' wave value at the mitral annulus between survivors and nonsurvivors of sepsis, as the S' wave measurement is limited by angle dependence and is a unidirectional (longitudinal) and unidimensional (one section) assessment, making it difficult to obtain optimal examination section images in critically ill patients with restricted body positions. Speckle tracking echocardiography (STE) has provided important insights into the early detection of cardiac dysfunction by measuring ventricular global longitudinal strain (GLS). However, the application of speckle tracking echocardiography in the assessment of myocardial function in sepsis is still in the early stages of exploration.

[0006] In summary, at present, the specific ultrasound parameters used for SIC and their significance have not been clarified. Moreover, due to the extremely complex clinical phenotype of septic cardiomyopathy and the unclear pathogenesis, these current situations have led to difficulties in the diagnosis of septic cardiomyopathy. From the above, it can be seen that relying solely on a single ultrasound parameter such as ventricular global longitudinal strain (GLS) or left ventricular ejection fraction (LVEF) cannot fully reflect cardiac function, and the multi-index combination parameters are unclear and lack quantitative standards. Therefore, it is urgent to construct a scheme that can quantitatively diagnose septic cardiomyopathy by combining multiple ultrasound parameters. Summary of the invention

[0007] The purpose of the present invention is to provide a method for constructing a diagnostic model of septic cardiomyopathy and a diagnostic system. By combining multimodal cardiac ultrasound data, the cardiac function of septic patients is comprehensively and dynamically quantitatively evaluated. The independent predictive factors of ultrasonic diagnosis of septic myocardium are determined by regression analysis and visualized, thereby achieving quantitative diagnosis of septic cardiomyopathy.

[0008] To achieve the above object, the present invention provides the following solutions: A method for constructing a sepsis cardiomyopathy diagnostic model comprises the following steps: S1. Multimodal data acquisition: dynamic acquisition of multimodal ultrasound data and clinical data of patients with sepsis; S2. Evaluate the overall and local systolic and diastolic function of the left and right ventricles of patients with septic cardiomyopathy based on multimodal ultrasound data, and make a preliminary diagnosis of septic cardiomyopathy based on the clinical data; S3. The multimodal ultrasound data of sepsis patients were divided into training and validation sets using the Rcaret package, and the training set was subjected to least absolute shrinkage and LASSO regression analysis using the glmnet R package to determine preliminary predictors of ultrasound diagnosis. S4. Performing logistic regression analysis on the preliminary predictive factors to determine independent predictive factors, wherein the independent predictive factors are used to reflect the cardiac function of patients with sepsis; S5. The independent predictors were back-translated into nomoscore using the rms package to obtain a nomogram, which visualized the independent predictors according to their weights and quantified the probability of septic cardiomyopathy.

[0009] Furthermore, the clinical data include demographic and clinical characteristics, clinical and laboratory data, and prognostic indicators; The demographic and clinical characteristics included age, sex, height, weight, primary diagnosis, site of infection, known etiology, and underlying diseases; The clinical and laboratory data included heart rate, mean arterial pressure, vasoactive drug dosage, pH, oxygenation index, acute physiology and chronic pathology score, infection-related acute organ function score, white blood cell count, neutrophil count, lymphocyte count, hematocrit level, platelet count, calcitonin level, C-reactive protein, interleukin-6, total bilirubin level, serum creatinine level, troponin I level, and pro-brain natriuretic peptide; The prognostic indicators include primary prognostic indicators and secondary prognostic indicators. The primary prognostic indicator is the 28-day mortality rate, and the secondary prognostic indicators are the duration of ventilator use and the duration of ICU stay.

[0010] Furthermore, the dynamic acquisition of multimodal ultrasound data specifically includes: On the 1st to 5th day after the patient entered the ICU, the cardiac function of the patients with sepsis was evaluated by multimodal cardiac ultrasound technology including two-dimensional imaging, M mode, color Doppler, pulsed Doppler, tissue Doppler and speckle tracking imaging. The evaluation criteria included the evaluation of left ventricular systolic and diastolic function, the evaluation of right ventricular systolic function, The evaluation of left ventricular systolic and diastolic function includes: left ventricular long axis strain measured by speckle tracking, left ventricular ejection fraction, left ventricular outflow tract time-velocity integral, early diastolic mitral flow velocity, late diastolic mitral flow velocity, E / A ratio, mitral annular tissue Doppler early diastolic velocity on the ventricular septum side and ventricular free wall side, E / e' ratio, left atrial volume index calculated by left atrial diameter measured by two-dimensional ultrasound, and maximum tricuspid regurgitation velocity; Assessment of right ventricular systolic function included measurement of tricuspid annular plane systolic excursion, tricuspid systolic blood flow velocity, and inferior vena cava collapsibility index.

[0011] Furthermore, the evaluation of the overall and local systolic and diastolic function of the left and right ventricles of the heart of a patient with sepsis specifically includes: The evaluation criteria for left ventricular systolic dysfunction were left ventricular ejection fraction less than 50%; Left ventricular diastolic dysfunction was defined as meeting at least two of the following criteria: tricuspid peak velocity greater than 2.8 m / s, left atrial volume greater than 34 mL / m², tissue Doppler imaging showing septal ring e′ wave velocity less than 7 cm / s, lateral ring less than 10 cm / s, lateral ring e′ ratio greater than 13, septal ring e′ ratio greater than 15; Right ventricular systolic dysfunction was defined as the fulfillment of at least two of the following criteria: tricuspid annular plane displacement less than 16 mm, tricuspid lateral annular velocity less than 15 cm / s, and right ventricular fractional area change less than 35%.

[0012] The present invention also provides a septic cardiomyopathy diagnostic model constructed according to the method for constructing a septic cardiomyopathy diagnostic model.

[0013] The present invention also provides a diagnostic system for septic cardiomyopathy, which is used to execute the method for constructing a diagnostic model for septic cardiomyopathy, comprising: Data acquisition module, used for dynamic acquisition of multimodal ultrasound data and clinical information of sepsis patients; An evaluation module, used to preliminarily evaluate the overall and local systolic and diastolic functions of the left and right ventricles of patients with septic cardiomyopathy based on multimodal ultrasound data, and to make a preliminary diagnosis of septic cardiomyopathy in combination with the clinical data; A preliminary predictor determination module was used to divide the multimodal ultrasound data of sepsis patients into a training set and a validation set using the Rcaret package, and to perform least absolute shrinkage and LASSO regression analysis on the training set using the glmnet R package to determine preliminary predictors of ultrasound diagnosis; Logistics analysis module, used to perform logistics regression analysis on preliminary predictive factors to determine independent predictive factors, wherein the independent predictive factors are used to reflect the cardiac function of patients with sepsis; The prediction visualization module is used to translate the independent predictors into nomoscore through the rms package to obtain a nomogram, visualize the independent predictors according to their weights, and quantify the probability of septic cardiomyopathy.

[0014] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects: the method and system for quantitative diagnosis of septic cardiomyopathy provided by the present invention comprehensively evaluate the cardiac function of septic patients based on multimodal echocardiography and establish a reliable ultrasonic diagnosis prediction model for septic cardiomyopathy. Independent predictive factors are screened out through the model to comprehensively reflect the cardiac function of septic patients and simplify the cardiac assessment process of septic patients. Moreover, the probability of SIC occurrence is quantified through visualization through nomoscore, and the weight of ultrasonic diagnostic predictive factors in SIC diagnosis is clarified. The present invention also confirms that the model has excellent performance in predicting SIC, and provides a visualization method with high sensitivity and specificity for early prediction of the occurrence of septic cardiomyopathy, which is convenient for clinical development and application and has far-reaching clinical significance.

[0015] In summary, the present invention solves the problems in the prior art that a single ultrasound parameter cannot fully reflect cardiac function, the multi-index combination parameters are unclear and lack quantitative standards, and the specific ultrasound parameters for SIC cannot be screened. The specific ultrasound parameters (i.e., 3 independent predictors) for SIC diagnosis are screened out. The present invention provides an intuitive method with high sensitivity and specificity for early prediction of the occurrence of SIC, improves the efficiency of SIC diagnosis, promotes clinical development and application, and has important clinical significance. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0017] Figure 1 is a flow chart of the method for constructing the septic cardiomyopathy diagnostic model of the present invention; Figure 2 Schematic diagram of using the LASSO regression analysis method for variable selection in an embodiment of the present invention, wherein Figure A represents the use of the LASSO regression model for variable selection, and Figure B represents the screening result of the LASSO regression model; Figure 3It is a forest plot of logistic regression analysis of predictive factors of septic cardiomyopathy risk in patients with sepsis in an embodiment of the present invention, wherein A represents logistic regression analysis of predictive factors of septic cardiomyopathy risk in patients with sepsis, and B represents independent predictors GLS, TAPSE and E predicted by SIC modal diagram. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] The purpose of the present invention is to provide a method for constructing a diagnostic model of septic cardiomyopathy and a diagnostic system. By combining multimodal cardiac ultrasound, the cardiac function of septic patients is comprehensively and dynamically evaluated, and the independent predictive factors of ultrasonic diagnosis of septic myocardium are determined by Lasso regression, thereby realizing the quantitative diagnosis of septic cardiomyopathy.

[0020] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0021] A method for constructing a septic cardiomyopathy diagnostic model provided in an embodiment of the present invention comprises the following steps: S1. Multimodal data acquisition: Dynamically acquire multimodal ultrasound data and clinical data of patients with sepsis, and make a preliminary diagnosis of septic cardiomyopathy based on the clinical data; S2. Evaluate the overall and local systolic and diastolic function of the left and right ventricles in patients with septic cardiomyopathy based on multimodal ultrasound data, and make a preliminary diagnosis of septic cardiomyopathy based on clinical data; S3. The multimodal ultrasound data of sepsis patients were divided into training and validation sets using the Rcaret package. The training set was subjected to least absolute shrinkage and selection operator (LASSO) regression analysis using the glmnet R package to determine preliminary predictors of ultrasound diagnosis. S4. Performing logistic regression analysis on the preliminary predictive factors to determine independent predictive factors, wherein the independent predictive factors are used to reflect the cardiac function of patients with sepsis; S5. The independent predictors were back-translated into nomoscore using the rms package to obtain a nomogram, which visualized the independent predictors according to their weights and quantified the probability of septic cardiomyopathy.

[0022] The specific implementation process of the above method is as follows: 1. Patients who were treated in a tertiary general hospital from March 2023 to April 2024 were selected as research subjects and screened according to the following inclusion and exclusion criteria: Inclusion criteria: 1) meeting the sepsis 3.0 diagnostic criteria; 2) age ≥ 18 years old.

[0023] Exclusion criteria: 1) patients with acute coronary syndrome or who received related surgery or intervention during hospitalization; 2) patients with a history of chronic heart failure, chronic renal insufficiency (requiring long-term dialysis) or chronic liver insufficiency (children grade C); 3) patients with a history of hypertrophic cardiomyopathy, dilated cardiomyopathy, restrictive cardiomyopathy, rheumatic heart disease, etc.; 4) patients with a history of severe arrhythmias; 5) patients who were unable to undergo echocardiography during ICU hospitalization for various reasons; 6) patients or their guardians who refused to participate in this study or withdrew midway.

[0024] Among them, 73 patients with acute or chronic cardiac dysfunction unrelated to septic cardiomyopathy or patients with end-stage functional failure caused by chronic organ diseases were excluded from the study to avoid misdiagnosis of septic cardiac dysfunction. Subsequently, 221 patients with sepsis underwent dynamic multimodal cardiac ultrasound. However, 40 patients were excluded from subsequent analysis due to incomplete dynamic cardiac ultrasound examination. Finally, a total of 181 patients with sepsis were considered eligible for analysis in this study, including 107 men and 74 women, aged between 19 and 86 years, with a median age of 58 years. The participants were randomly assigned to the training set and the validation set in a ratio of 7:3, with 126 cases in the training set and 55 cases in the validation set. All patients underwent necessary examinations.

[0025] 2. Dynamic acquisition of multimodal ultrasound data For patients who met the above criteria, cardiac function in patients with sepsis was assessed using multimodal echocardiography including two-dimensional imaging, M mode, color Doppler, pulsed Doppler, tissue Doppler, and speckle tracking imaging on days 1 to 5 after admission to the ICU. The evaluation criteria covered the assessment of left ventricular systolic and diastolic function, including left ventricular long-axis strain (GLS) measured by speckle tracking, left ventricular ejection fraction (LVEF), left ventricular outflow tract time-velocity integral (VTI), early diastolic mitral velocity (E), late diastolic mitral velocity (A), E / A ratio, mitral annular tissue Doppler early diastolic velocity (e', on the ventricular septal side (e'-S) and ventricular free wall side (e'-L)), E / e' ratio, left atrial volume index (LAVI) calculated from left atrial diameter measured by two-dimensional echocardiography, and maximum tricuspid regurgitation velocity (TRV). In addition, the assessment of right ventricular systolic function was included, including measurement of tricuspid annular plane systolic excursion (TAPSE), tricuspid systolic velocity (S), and inferior vena cava collapsibility index (IVC-CI).

[0026] A total of 14 ultrasound factors were obtained during this process. Standardized ultrasound examination procedures were used to ensure optimal image acquisition and data collection. Multimodal ultrasound data were used to quantitatively and comprehensively evaluate the global and regional systolic and diastolic function of the left and right ventricles in septic cardiomyopathy.

[0027] 3. Clinical Data Collection (1) Demographic and clinical characteristics: age, sex, height, weight, primary diagnosis, site of infection, etiology (if known), underlying diseases (hypertension, diabetes, coronary artery disease, chronic kidney disease, chronic obstructive pulmonary disease, neoplastic disease, autoimmune disease, etc.).

[0028] (2) Clinical and laboratory data: heart rate, mean arterial pressure, dosage of vasoactive drugs (such as norepinephrine, dopamine, dobutamine), pH, oxygenation index, acute physiology and chronic pathology evaluation (APACHE II) score, infection-related acute organ function evaluation (SOFA) score, white blood cell count, neutrophil count, lymphocyte count, hematocrit level, platelet count, calcitonin level, C-reactive protein, interleukin-6, total bilirubin level, serum creatinine level, troponin I level, and pro-brain natriuretic peptide (NT-proBNP).

[0029] (3) Prognostic indicators: The primary prognostic indicator was the 28-day mortality rate, and the secondary prognostic indicators were the duration of ventilator use (h) and the duration of ICU stay (h).

[0030] 4. Diagnostic criteria for septic cardiomyopathy The patients with sepsis were included in the study based on the following conditions, and a physician with more than ten years of ICU experience and a professional title of associate senior or above made a comprehensive assessment of whether they had septic cardiomyopathy based on their medical history: (1) acute and reversible, with at least 2-3 dynamic multimodal ultrasound examinations; (2) global and biventricular dysfunction (systolic and / or diastolic) with decreased contractility; (3) elevated myocardial injury markers (troponin I > 0.012 ng / ml and NT-proBNP > 300 pg / ml); and (4) myocardial ischemia caused by acute coronary artery stenosis was excluded.

[0031] The echocardiographic report defines left ventricular systolic dysfunction (LVSDF) as a left ventricular ejection fraction (LVEF) less than 50%.

[0032] The diagnostic criteria for left ventricular diastolic dysfunction (LVDDF) are: at least two of the following criteria are met: tricuspid peak flow velocity greater than 2.8 m / s, left atrial volume greater than 34 mL / m², tissue Doppler imaging showing septal annular e′ wave velocity less than 7 cm / s and lateral annular e′ wave velocity less than 10 cm / s, lateral annular e′ ratio greater than 13, and septal annular e′ ratio greater than 15.

[0033] The diagnostic criteria for right ventricular systolic dysfunction (RVSDF) were: at least two of the following criteria were met: tricuspid valve systolic annular plane displacement less than 16 mm, tricuspid valve systolic lateral annular velocity less than 15 cm / s, and right ventricular fractional area change less than 35%.

[0034] 5. Statistical methods The Shapiro-Wilk normality test was used to assess whether the data distribution of continuous variables was normal. The mean and standard deviation were used to describe the data with normal distribution and compared using the independent sample t test. For non-normally distributed data, the median and interquartile range were used to summarize and compared using the Mann-Whitney U test. Descriptive statistics included the frequency of categorical variables expressed as percentage (%) and compared using the chi-square test or Fisher's exact test.

[0035] Statistical analysis was performed using the Rcaret package (version 4.2.1). First, 181 patients with sepsis were randomly assigned to a training set (126 cases) and a validation set (55 cases) using the R caret package, with an allocation ratio of 7:3. Subsequently, the glmnet package was used to perform LASSO (least absolute shrinkage and selection operator) regression analysis, which is a method for scaling and selecting variables in linear regression models to achieve univariate analysis. Predictor variables are selected by minimizing the prediction error of quantitative response variables using LASSO regression. LASSO regression scales the regression coefficients of certain variables toward zero. In the LASSO regression analysis using R software for ten-fold cross-validation, variables with non-zero coefficients are considered to have the strongest correlation with the response variable. The process involves standardizing and normalizing the variables to determine the optimal lambda value, where Lambda.1se produces a model with good performance and fewer independent variables. As Figure 2 As shown, on the training set, according to the specified inclusion criteria, the LASSO regression analysis method was used to determine four preliminary predictors, namely GLS, e'-L, E and TAPSE.

[0036] 6. Establishment and visualization of the diagnostic model for septic cardiomyopathy like Figure 3 As shown, logistic regression analysis was performed using the R language glm package, and a predictive diagnostic model was constructed in combination with the features selected in the LASSO regression model. A SIC risk prediction model was established by introducing and analyzing statistically significant predictors. All features selected in this embodiment were statistically significant and used to create a nomogram prediction model. The nomogram diagram was developed using the rms package in the R language.

[0037] 7. Research Results Between March 2023 and April 2024, 294 patients with sepsis were initially screened. Of these participants, 110 were diagnosed with SIC, while 71 were not diagnosed, with a prevalence of SIC in this cohort of 60.77%. Example 2

[0038] The embodiment of the present invention provides a diagnostic model for septic cardiomyopathy constructed according to the diagnostic method for septic cardiomyopathy described in Example 1. The performance of the model is verified as follows: The performance of the diagnostic model was evaluated by discrimination ability, calibration ability, and clinical validity. Discrimination ability was evaluated by the area under the receiver operating characteristic curve (AUC); calibration accuracy was determined by visual calibration plots and the Hosmer-Lemeshow test; and clinical validity was analyzed by decision curve analysis.

[0039] In order to avoid overfitting, 500 self-sampling internal validations were performed on the prediction efficiency, and a two-tailed p value less than 0.05 was considered statistically significant. The specific results are as follows: First, the ROC curve was used to evaluate the classification ability of the predictive diagnosis model. For this model, the comprehensive area under the ROC curve of the training set was 0.879 (95% confidence interval (CI) was 0.821-0.936), and the comprehensive area under the ROC curve of the validation set was 0.888 (95% CI was 0.801-0.976), indicating that the model had accurate predictive performance.

[0040] The diagnostic model was calibrated using calibration graphs and Hosmer-Lemeshow tests, and the results showed that the predicted probability of the model was consistent with the actual probability, indicating that the model fit was good. The results of the Hosmer-Lemeshow test showed that the consistency between the predicted probability and the observed results was high in both the training set and the validation set (P = 0.386). (p = 0.957).

[0041] Decision curve analysis (DCA) showed that the threshold probability of the diagnostic model varied between 5% and 100% in the training set and between 21% and 100% in the validation set, indicating that the model had considerable net clinical benefit. Example 3

[0042] The embodiment of the present invention provides a diagnostic system for septic cardiomyopathy, which is used to execute the method for constructing a diagnostic model for septic cardiomyopathy described in Example 1, comprising: Data acquisition module, used for dynamic acquisition of multimodal ultrasound data and clinical information of sepsis patients; An evaluation module, used to preliminarily evaluate the overall and local systolic and diastolic functions of the left and right ventricles of patients with septic cardiomyopathy based on multimodal ultrasound data, and to make a preliminary diagnosis of septic cardiomyopathy in combination with the clinical data; A preliminary predictor determination module was used to divide the multimodal ultrasound data of sepsis patients into a training set and a validation set using the Rcaret package, and to perform least absolute shrinkage and LASSO regression analysis on the training set using the glmnet R package to determine preliminary predictors of ultrasound diagnosis; Logistics analysis module, used to perform logistics regression analysis on preliminary predictive factors to determine independent predictive factors, wherein the independent predictive factors are used to reflect the cardiac function of patients with sepsis; The prediction visualization module is used to translate the independent predictors into nomoscore through the rms package to obtain a nomogram, visualize the independent predictors according to their weights, and quantify the probability of septic cardiomyopathy.

[0043] In summary, the diagnostic method, system and diagnostic model of septic cardiomyopathy provided by the present invention comprehensively evaluate the cardiac function of septic patients based on multimodal echocardiography, and establish a diagnostic model for septic cardiomyopathy. Through the model, three SIC ultrasonic diagnostic predictors are screened out to comprehensively reflect the cardiac function of septic patients and simplify the bedside cardiac assessment process for septic patients. The predictors are visualized according to their weights through nomoscore, the probability of SIC occurrence is quantified, and the weight of ultrasonic diagnostic predictors in SIC diagnosis is clarified. It is confirmed that the model has excellent performance in predicting SIC, and provides a visualization method with high sensitivity and specificity for early prediction of the occurrence of septic cardiomyopathy, which is convenient for clinical development and application and has far-reaching clinical significance.

[0044] The remaining technical features in this embodiment can be flexibly selected by those skilled in the art according to actual conditions to meet different specific practical needs. However, it is obvious to those skilled in the art that these specific details are not necessary to implement the present invention.

[0045] Modifications and changes made by those skilled in the art that do not depart from the spirit and scope of the present invention should be within the scope of protection of the claims attached to the present invention. In the above description, a large number of specific details are set forth in order to provide a thorough understanding of the present invention. However, it is obvious to those of ordinary skill in the art that these specific details are not necessary to practice the present invention. In other examples, in order to avoid confusing the present invention, well-known technologies, such as specific construction details, operating conditions and other technical conditions, are not specifically described.

[0046] The principles and implementation methods of the present invention are described in this article using specific examples. The description of the above embodiments is only used to help understand the method and core idea of ​​the present invention. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A method for constructing a diagnostic model for septic cardiomyopathy, characterized in that: The following steps are involved: S1. Multimodal data acquisition: dynamic acquisition of multimodal ultrasound data and clinical data of patients with sepsis; S2. Evaluate the overall and local systolic and diastolic function of the left and right ventricles of patients with septic cardiomyopathy based on multimodal ultrasound data, and make a preliminary diagnosis of septic cardiomyopathy in combination with the clinical data; S3. The multimodal ultrasound data of sepsis patients were divided into training and validation sets using the R caret package, and the training set was subjected to least absolute shrinkage and LASSO regression analysis using the glmnet R package to determine preliminary predictors of ultrasound diagnosis. S4. Performing logistic regression analysis on the preliminary predictive factors to determine independent predictive factors, wherein the independent predictive factors are used to reflect the cardiac function of patients with sepsis; S5. The independent predictors were back-translated into nomoscore using the rms package to obtain a nomogram, which visualized the independent predictors according to their weights and quantified the probability of septic cardiomyopathy.

2. The method for constructing a diagnostic model for septic cardiomyopathy according to claim 1, characterized in that: The clinical data included demographic and clinical characteristics, clinical and laboratory data, and prognostic indicators; The demographic and clinical characteristics included age, sex, height, weight, primary diagnosis, site of infection, known etiology, and underlying diseases; The clinical and laboratory data included heart rate, mean arterial pressure, vasoactive drug dosage, pH, oxygenation index, acute physiology and chronic pathology score, infection-related acute organ function score, white blood cell count, neutrophil count, lymphocyte count, hematocrit level, platelet count, calcitonin level, C-reactive protein, interleukin-6, total bilirubin level, serum creatinine level, troponin I level, and pro-brain natriuretic peptide; The prognostic indicators include primary prognostic indicators and secondary prognostic indicators. The primary prognostic indicator is the 28-day mortality rate, and the secondary prognostic indicators are the duration of ventilator use and the duration of ICU stay.

3. The method for constructing a diagnostic model for septic cardiomyopathy according to claim 1, characterized in that: The dynamic acquisition of multi-modal ultrasound data specifically includes: On the 1st to 5th day after the patient entered the ICU, the cardiac function of the patients with sepsis was evaluated by multimodal cardiac ultrasound technology including two-dimensional imaging, M mode, color Doppler, pulsed Doppler, tissue Doppler and speckle tracking imaging. The evaluation criteria included the evaluation of left ventricular systolic and diastolic function, the evaluation of right ventricular systolic function, The evaluation of left ventricular systolic and diastolic function includes: left ventricular long axis strain measured by speckle tracking, left ventricular ejection fraction, left ventricular outflow tract time-velocity integral, early diastolic mitral flow velocity, late diastolic mitral flow velocity, E / A ratio, mitral annular tissue Doppler early diastolic velocity on the ventricular septum side and ventricular free wall side, E / e' ratio, left atrial volume index calculated by left atrial diameter measured by two-dimensional ultrasound, and maximum tricuspid regurgitation velocity; The evaluation of right ventricular systolic function includes measuring tricuspid annular plane systolic displacement, tricuspid systolic blood flow velocity and inferior vena cava collapsibility index.

4. The method for constructing a diagnostic model for septic cardiomyopathy according to claim 1, characterized in that: The evaluation of the overall and local systolic and diastolic function of the left and right ventricles of the heart of a patient with sepsis specifically includes: The evaluation criteria for left ventricular systolic dysfunction were left ventricular ejection fraction less than 50%; Left ventricular diastolic dysfunction was defined as meeting at least two of the following criteria: tricuspid peak velocity greater than 2.8 m / s, left atrial volume greater than 34 mL / m², tissue Doppler imaging showing septal ring e′ wave velocity less than 7 cm / s and lateral ring less than 10 cm / s, lateral ring e′ ratio greater than 13, and septal ring e′ ratio greater than 15; Right ventricular systolic dysfunction was defined as meeting at least two of the following criteria: tricuspid annular plane displacement less than 16 mm, tricuspid lateral annular velocity less than 15 cm / s, and right ventricular fractional area change less than 35%.

5. A septic cardiomyopathy diagnostic model constructed according to the method for constructing a septic cardiomyopathy diagnostic model according to any one of claims 1 to 4.

6. A diagnostic system for septic cardiomyopathy, used to execute the method for constructing a diagnostic model for septic cardiomyopathy according to any one of claims 1 to 4, characterized in that: include: Data acquisition module, used for dynamic acquisition of multimodal ultrasound data and clinical information of sepsis patients; An evaluation module, used to preliminarily evaluate the overall and local systolic and diastolic functions of the left and right ventricles of patients with septic cardiomyopathy based on multimodal ultrasound data, and to make a preliminary diagnosis of septic cardiomyopathy in combination with the clinical data; A preliminary predictor determination module was used to divide the multimodal ultrasound data of sepsis patients into a training set and a validation set using the Rcaret package, and to perform least absolute shrinkage and LASSO regression analysis on the training set using the glmnet R package to determine preliminary predictors of ultrasound diagnosis; Logistics analysis module, used to perform logistics regression analysis on preliminary predictive factors to determine independent predictive factors, wherein the independent predictive factors are used to reflect the cardiac function of patients with sepsis; The prediction visualization module is used to translate the independent predictors into nomoscore through the rms package to obtain a nomogram, visualize the independent predictors according to their weights, and quantify the probability of septic cardiomyopathy.

Images