Establishment and Effectiveness Evaluation of a Scoring System-RAAS (RDW, AGE, APACHE II, SOFA) for Sepsis by a Retrospective Analysis

DEVELOPMENT AND VALIDATION OF A NOMOGRAM FOR PREDICTING 28-DAY IN-HOSPITAL MORTALITY IN SEPSIS PATIENTS BASED ON AN OPTIMIZED ACUTE PHYSIOLOGY AND CHRONIC HEALTH EVALUATION II SCORE

ABSTRACT

Purpose : The objective of this study is to establish a nomogram that correlates optimized Acute Physiology and Chronic Health Evaluation II (APACHE II) score with sepsis-related indicators, aiming to provide a robust model for early prediction of sepsis prognosis in clinical practice and serve as a valuable reference for improved diagnosis and treatment strategies. Methods : This retrospective study extracted sepsis patients meeting the inclusion criteria from the MIMIC-IV database to form the training group. An optimized APACHE II score integrated with relevant indicators was developed using a nomogram for predicting the prognosis of sepsis patients. External validation was conducted using data from the intensive care unit at Lanzhou University Second Hospital. Results : The study enrolled 1805 patients in the training cohort and 203 patients in the validation cohort. A multifactor analysis was conducted to identify factors affecting patient mortality within 28 days, resulting in the development of an optimized score by simplifying evaluation indicators from APACHE II score. The results showed that the optimized score (area under the ROC curve [AUC] = 0.715) had a higher area under receiver operating characteristic curve than Sequential Organ Failure Assessment score (AUC = 0.637) but slightly lower than APACHE II score (AUC = 0.720). Significant indicators identified through multifactor analysis included platelet count, total bilirubin level, albumin level, prothrombin time, activated partial thromboplastin time, mechanical ventilation use and renal replacement therapy use. These seven indicators were combined with optimized score to construct a nomogram based on these seven indicators. The nomogram demonstrated good clinical predictive value in both training cohort (AUC = 0.803) and validation cohort (AUC = 0.750). Calibration curves and decision curve analyses also confirmed its good predictive ability, surpassing the APACHE II score and Sequential Organ Failure Assessment score in identifying high-risk patients. Conclusions : The nomogram was established in this study using the MIMIC-IV database and validated with external data, demonstrating its robust discriminability, calibration, and clinical practicability for predicting 28-day mortality in sepsis patients. These findings aim to provide substantial support for clinicians' decision making.

Assessment of Sepsis Risk at Admission to the Emergency Department: Clinical Interpretable Prediction Model

This study aims to develop an interpretable prediction model based on explainable artificial intelligence to predict bacterial sepsis and discover important biomarkers. A total of 1572 adult patients, 560 of whom were sepsis positive and 1012 of whom were negative, who were admitted to the emergency department with suspicion of sepsis, were examined. We investigated the performance characteristics of sepsis biomarkers alone and in combination for confirmed sepsis diagnosis using Sepsis-3 criteria. Three different tree-based algorithms-Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), Adaptive Boosting (AdaBoost)-were used for sepsis prediction, and after examining comprehensive performance metrics, descriptions of the optimal model were obtained with the SHAP method. The XGBoost model achieved accuracy of 0.898 (0.868-0.929) and area under the ROC curve (AUC) of 0.940 (0.898-0.980) with a 95% confidence interval. The five biomarkers for predicting sepsis were age, respiratory rate, oxygen saturation, procalcitonin, and positive blood culture. SHAP results revealed that older age, higher respiratory rate, procalcitonin, neutrophil-lymphocyte count ratio, C-reactive protein, plaque, leukocyte particle concentration, as well as lower oxygen saturation, systolic blood pressure, and hemoglobin levels increased the risk of sepsis. As a result, the Explainable Artificial Intelligence (XAI)-based prediction model can guide clinicians in the early diagnosis and treatment of sepsis, providing more effective sepsis management and potentially reducing mortality rates and medical costs.

Association Between Plasma Levels of Monocyte Chemoattractant Protein-1 (MCP-1) and 28-Day Mortality in Elderly Patients with Sepsis: A Retrospective Single-Center Study

BACKGROUND Previous studies have identified an association between plasma levels of the inflammatory cytokine, monocyte chemoattractant protein-1 (MCP-1), and outcomes for patients with sepsis. This retrospective single-center study assessed the association between plasma levels of MCP-1 and 28-day mortality in 136 patients ≥65 years diagnosed with sepsis between October 2020 and October 2021. MATERIAL AND METHODS The objective was to compare and analyze the parameters in the survival group (n=35) and the 28-day mortality group (n=101), including Sequential Organ Failure Assessment (SOFA), Acute Physiology and Chronic Health Evaluation II (APACHE II), plasma MCP-1, and laboratory test results. Plasma MCP-1 was quantified by cytokine test kit (LKTM014B, R&D). Statistical analysis was carried out in SPSS 26.0 and MedCalc 92.1.0 software. RESULTS The 28-day mortality group exhibited higher levels of SOFA, APACHEII, and plasma MCP-1 (all P<0.001), as well as lower levels of albumin, compared to the survival group (P<0.05). The logistic regression analysis findings indicated that SOFA, APACHEII, plasma MCP-1, and SBP are all independent risk factors for 28-day mortality. The area under the curve for SOFA, APACHEII, MCP-1, MCP-1+ SOFA, and MCP-1+APACHEII were 0.845, 0.744, 0.712, 0.879, and 0.822, respectively. MCP-1+SOFA exhibited higher sensitivity than SOFA alone. Furthermore, the assessment values of plasma MCP-1 combined with SOFA were superior to those of APACHE II or plasma MCP-1 (Z₁=2.661, Z₂=3.272, both P<0.01). CONCLUSIONS The findings from this study from a single center support those of previous studies that increased plasma levels of MCP-1 are significantly associated with 28-day mortality in patients with sepsis.

Diagnostic and prognostic role of platelets in patients with sepsis and septic shock

Studies investigating the prognostic role of platelets commonly include critically ill patients, whereas data regarding the prognostic impact of platelet count in patients admitted with sepsis and septic shock is limited. Therefore, the study investigates the prognostic role of platelet count in patients with sepsis and septic shock. Consecutive patients with sepsis and septic shock from 2019 to 2021 were included monocentrically. Blood samples were retrieved from the day of disease onset (day 1), days 2, 3, 5, 7 and 10. Firstly, the diagnostic value of platelet count was tested for septic shock compared to sepsis. Secondly, the prognostic value of platelet count was tested for 30-day all-cause mortality. Statistical analyses included univariable t-test, Spearman's correlation, C-statistics, Kaplan-Meier analyses, as well as multivariable mixed analysis of variance (ANOVA), Cox proportional regression analyses and propensity score matching. A total of 358 patients with sepsis and septic shock were included with a median platelet count of 176 × 10⁶/ml. The presence of thrombocytopenia (i.e. <150 × 10⁶/ml) was associated with increased risk of 30-day mortality (HR = 1.409; 95% CI 1.057-1.878; p = .019), which was still demonstrated after propensity score matching. During the course of sepsis, a nadir was observed on sepsis day 5 with a decrease in the mean platelet count by 21.5%. Especially serum lactate, mean arterial pressure and the presence of malignancies were found to predict platelet decline during the course of sepsis/septic shock. The presence of platelet decline >25% was associated with an increased risk of 30-day all-cause mortality (HR = 1.484; 95% CI 1.045-2.109; p = .028). Following platelet decline, recovery was observed from day 5 to day 10 (mean increase 7.5%). However, platelet recovery was not found to be associated with 30-day all-cause mortality (HR = 1.072; 95% CI 0.567-2.026; p = .832). In conclusion, both thrombocytopenia and platelet decline during the course of sepsis were associated with an increased risk of 30-day all-mortality in patients admitted with sepsis or septic shock.

A simplified machine learning model utilizing platelet-related genes for predicting poor prognosis in sepsis

Background

Thrombocytopenia is a known prognostic factor in sepsis, yet the relationship between platelet-related genes and sepsis outcomes remains elusive. We developed a machine learning (ML) model based on platelet-related genes to predict poor prognosis in sepsis. The model underwent rigorous evaluation on six diverse platforms, ensuring reliable and versatile findings.

Methods

A retrospective analysis of platelet data from 365 sepsis patients confirmed the predictive role of platelet count in prognosis. We employed COX analysis, Least Absolute Shrinkage and Selection Operator (LASSO) and Support Vector Machine (SVM) techniques to identify platelet-related genes from the GSE65682 dataset. Subsequently, these genes were trained and validated on six distinct platforms comprising 719 patients, and compared against the Acute Physiology and Chronic Health Evaluation II (APACHE II) and Sequential Organ-Failure Assessment (SOFA) score.

Results

A PLT count <100×109/L independently increased the risk of death in sepsis patients (OR = 2.523; 95% CI: 1.084-5.872). The ML model, based on five platelet-related genes, demonstrated impressive area under the curve (AUC) values ranging from 0.5 to 0.795 across various validation platforms. On the GPL6947 platform, our ML model outperformed the APACHE II score with an AUC of 0.795 compared to 0.761. Additionally, by incorporating age, the model's performance was further improved to an AUC of 0.812. On the GPL4133 platform, the initial AUC of the machine learning model based on five platelet-related genes was 0.5. However, after including age, the AUC increased to 0.583. In comparison, the AUC of the APACHE II score was 0.604, and the AUC of the SOFA score was 0.542.

Conclusion

Our findings highlight the broad applicability of this ML model, based on platelet-related genes, in facilitating early treatment decisions for sepsis patients with poor outcomes. Our study paves the way for advancements in personalized medicine and improved patient care.

D-DI/PLT can be a prognostic indicator for sepsis

Aims

To investigate the indicators affecting the early outcome of patients with sepsis and to explore its prognostic efficacy for sepsis.

Methods

We collected clinical data from 201 patients with sepsis admitted to the emergency department of Xijing Hospital between June 2019 and June 2022. The patients were categorized into groups (survival or fatality) based on their 28-day prognosis. The clinical characteristics, biochemical indexes, organ function-related indicators, and disease scores of the patients were analyzed for both groups. Risk factor analysis was conducted for the indicators with significant differences.

Results

Among the indicators with significant differences between the deceased and survival groups, D-dimer (D-DI), Sequential Organ Failure Assessment (SOFA) score, platelet (PLT), international normalized ratio (INR), and D-DI/PLT were identified as independent risk factors affecting the prognosis of sepsis patients. Receiver operating characteristic (ROC) curves showed that D-DI/PLT (area under the curve (AUC) = 93.9), D-DI (AUC = 89.6), PLT (AUC = 81.3), and SOFA (AUC = 78.4) had good judgment efficacy. Further, Kaplan Meier (K-M) survival analysis indicated that the 28-day survival rates of sepsis patients were significantly decreased when they had high levels of D-DI/PLT, D-DI, and SOFA as well as low PLTs. The hazard ratio (HR) of D-DI/PLT between the two groups was the largest (HR = 16.19).

Conclusions

D-DI/PLT may be an independent risk factor for poor prognosis in sepsis as well as a clinical predictor of patient prognosis.

Comparing the clinical and economic efficiency of four natural surfactants in treating infants with respiratory distress syndrome

Surfactant therapy has revolutionized the treatment of respiratory distress syndrome (RDS) over the past few decades. Relying on a new method, the current research seeks to compare four common surfactants in the health market of Iran to determine the best surfactant according to the selected criteria. The research was a cross-sectional, retrospective study that used the data of 13,169 infants as recorded on the information system of the Iranian Ministry of Health. To rank the surfactants used, the following indicators were measured: re-dosing rate, average direct treatment cost, average length of stay, disease burden, need for invasive mechanical ventilation, survival at discharge, and medical referrals. The CRITIC (criteria importance through intercriteria correlation) method was used to determine the weight of the indicators, and MABAC (multi-attributive border approximation area comparison) was used to prioritize the surfactants. Based on the seven selected indicators in this research (re-dosing rate, average length of stay, direct medical cost per one prescription, medical referral rate, survival at discharge, disability-adjusted life years, number of newborns in need of invasive mechanical ventilation) and using multi-criteria analysis method, Alveofact was identified as the worst surfactant in infants with either more or less than 32 weeks' gestation. So that some criteria were worse in Alveofact group infants than other groups; for example, in the comparison of the Alveofact group with the average of the total population, it was found that the survival rate at discharge was 57.14% versus 66.43%, and the rate of re-dosing was 1.63 versus 1.39. BLES (bovine lipid extract surfactant) was the best alternative for infants more than 32 weeks' gestation, whereas Survanta was identified as best option for infants with less than 32 weeks' gestation. Curosurf showed an average level of functionality in the ranking. This study advises the policy makers in the field of neonatal health to increase the market share of more effective surfactants based on this study and other similar studies. On the other hand, neonatal health care providers are also advised to prioritize the use of more effective surfactants if possible, depending on the clinical conditions and desired improvements.

Diagnostic value of RDW for the prediction of mortality in adult sepsis patients: A systematic review and meta-analysis

Background

Red blood cell distribution width (RDW) is a common biomarker of bacterial infections, and it can be easily obtained from a routine blood test. We investigate the diagnostic value of RDW for the prediction of mortality in adult sepsis patients through a review and meta-analysis. We registered this review in PROSPERO (Registration Number: CRD42022357712), and the details of the registration are included in Appendix 1.

Methods

We searched PubMed, Cochrane Library, Springer, and Embase between Jan. 1, 2000, and May 30, 2022, for primary studies about this research. We collected articles that investigated RDW for varying degrees of sepsis patients—those who suffered from sepsis, severe sepsis, or sepsis shock. Studies of healthy people and sepsis of children and neonates were excluded from our research. The definition of study characteristics and data extraction were finished by two independent researchers and discrepancies resolved by consensus. The combined sensitivities and specificities were calculated by meta-analysis using STATA14.0. The sensitivity of the included studies was analyzed by excluding studies that had potential heterogeneity. A summary operating characteristic curve was made to evaluate the diagnostic value for the prediction of mortality in adult sepsis patients. The Fagan test was used to explore likelihood ratios and posttest probabilities. Finally, we investigated the source of heterogeneity using meta-regression.

Results

Twenty-four studies, including 40,763 cases altogether, were included in this analysis. Bivariate analysis indicated a combined sensitivity of 0.81 (95% CI 0.73–0.86) and specificity of 0.65 (95% CI 0.54–0.75). The area under the summary receiver operating characteristic curve was 0.81 (95% CI 0.77–0.84). Substantial heterogeneity resided in the studies (I^{2 =}96.68, 95% CI 95.95–97.4). Meta-regression showed that the reference description, prospective design, and blinded interpretation of the included studies could be responsible for the heterogeneity.

Conclusions

RWD is an available and valuable biomarker for prediction of mortality in adult sepsis patients.

Systematic review registration

https://www.crd.york.ac.uk/PROSPERO/, identifier CRD42022357712.

The value of NSE to predict ICU mortality in patients with septic shock: A prospective observational study

To investigate the predictive value of neuron-specific enolase (NSE) on intensive care unit (ICU) mortality in patients with septic shock. Seventy-five patients with septic shock hospitalized in the emergency intensive care unit (EICU) of Hebei General Hospital from March 2020 to September 2021 were included, and the patients' baseline characteristics and laboratory findings were collected. NSE levels on the first and fourth days after admission were retrieved. NSE% [(NSEday1 - NSEday4)/NSEday1 × 100%] and δNSE (NSEday1 - NSEday4) were calculated. The outcome indicator was ICU mortality. The patients were divided into the survivors group (n = 57) and the nonsurvivors group (n = 18). Multivariate analysis was performed to assess the relationship between NSE and ICU mortality. The predictive value of NSE was evaluated using receiver operating characteristic (ROC) curve. There were no significant differences in age, gender, systolic blood pressure (SBP), heart rate (HR), acute physiology and chronic health evaluation II score (APACHE II score), source of infection, and comorbidities between the 2 groups (all P > .05). Interleukin-6 (IL-6), NSE (day1), and NSE (day4) were significantly higher in patients in the nonsurvivors group (all P < .05), and there were no statistical differences in other laboratory tests between the 2 groups (all P > .05). APACHE II score, IL-6, lactate (Lac), total bilirubin (TBil), NSE (day1), and NSE (day4) showed a weak positive correlation with ICU mortality in patients with septic shock (all P < .05). Multivariate logistic regression analysis demonstrated that APACHE II score (odds ratio [OR] = 1.166, 95% confidence interval [95% confidence interval [CI]] 1.005-1.352, P = .042), IL-6 (OR = 1.001, 95% CI 1.000-1.001, P = .003) and NSE (day4) (OR = 1.099, 95% CI 1.027-1.176, P = .006) were independently associated with the ICU mortality of sepsis shock patients. The area under the curve (AUCs) of APACHE II score, IL-6, NSE (day1), and NSE (day4) for predicting prognosis were 0.650, 0.694, 0.758 and 0.770, respectively (all P < .05). NSE(day4) displayed good sensitivity and specificity (Sn = 61.11%, Sp = 91.23%) for predicting ICU mortality with a cutoff value of 25.94 ug/L. High-level NSE (day4) is an independent predictor of ICU mortality in sepsis shock patients, which may become a good alternate option for evaluating sepsis severity. More extensive studies are needed in the future to demonstrate the prognosis value of NSE.

Red cell distribution width and in-hospital mortality in septic shock: A public database research

OBJECTIVE

This study aimed to explore the relationship between red cell distribution width (RDW) and in-hospital mortality in septic shock based on a large-scale public database.

METHODS

All patients with septic shock in MIMIC-IV were enrolled. Based on RDW values, the general characteristics of different groups were compared. Different models were constructed for exploring the association of RDW and in-hospital mortality. To assess the predictive value of RDW, receiver operator characteristic (ROC) curve analysis was applied.

RESULTS

A total of 3006 patients with septic shock were included and in-hospital mortality was 32.27% (n = 970). The results of the fully adjusted model demonstrated that RDW was positively associated with in-hospital mortality in septic shock patients after adjusting all confounders (OR = 1.12, 95% CI:1.08-1.17, p < .001). A linear relationship between RDW and in-hospital mortality was found. For predicting in-hospital mortality, the area under the ROC curve (AUC) of RDW was .602 and the best threshold of RDW was 17.25%.

CONCLUSION

RDW was associated with in-hospital mortality in septic shock. It could be a useful marker for predicting clinical outcomes in septic shock.