Clinical usefulness of biomarkers for diagnosis and prediction of prognosis in sepsis and septic shock

Comparison between traditional logistic regression and machine learning for predicting mortality in adult sepsis patients

Background

Sepsis is a life-threatening disease associated with a high mortality rate, emphasizing the need for the exploration of novel models to predict the prognosis of this patient population. This study compared the performance of traditional logistic regression and machine learning models in predicting adult sepsis mortality.

Objective

To develop an optimum model for predicting the mortality of adult sepsis patients based on comparing traditional logistic regression and machine learning methodology.

Methods

Retrospective analysis was conducted on 606 adult sepsis inpatients at our medical center between January 2020 and December 2022, who were randomly divided into training and validation sets in a 7:3 ratio. Traditional logistic regression and machine learning methods were employed to assess the predictive ability of mortality in adult sepsis. Univariate analysis identified independent risk factors for the logistic regression model, while Least Absolute Shrinkage and Selection Operator (LASSO) regression facilitated variable shrinkage and selection for the machine learning model. Among various machine learning models, which included Bagged Tree, Boost Tree, Decision Tree, LightGBM, Naïve Bayes, Nearest Neighbors, Support Vector Machine (SVM), and Random Forest (RF), the one with the maximum area under the curve (AUC) was chosen for model construction. Model validation and comparison with the Sequential Organ Failure Assessment (SOFA) and the Acute Physiology and Chronic Health Evaluation (APACHE) scores were performed using receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA) curves in the validation set.

Results

Univariate analysis was employed to assess 17 variables, namely gender, history of coronary heart disease (CHD), systolic pressure, white blood cell (WBC), neutrophil count (NEUT), lymphocyte count (LYMP), lactic acid, neutrophil-to-lymphocyte ratio (NLR), red blood cell distribution width (RDW), interleukin-6 (IL-6), prothrombin time (PT), international normalized ratio (INR), fibrinogen (FBI), D-dimer, aspartate aminotransferase (AST), total bilirubin (Tbil), and lung infection. Significant differences (p < 0.05) between the survival and non-survival groups were observed for these variables. Utilizing stepwise regression with the "backward" method, independent risk factors, including systolic pressure, lactic acid, NLR, RDW, IL-6, PT, and Tbil, were identified. These factors were then incorporated into a logistic regression model, chosen based on the minimum Akaike Information Criterion (AIC) value (98.65). Machine learning techniques were also applied, and the RF model, demonstrating the maximum Area Under the Curve (AUC) of 0.999, was selected. LASSO regression, employing the lambda.1SE criteria, identified systolic pressure, lactic acid, NEUT, RDW, IL6, INR, and Tbil as variables for constructing the RF model, validated through ten-fold cross-validation. For model validation and comparison with traditional logistic models, SOFA, and APACHE scoring.

Conclusion

Based on deep machine learning principles, the RF model demonstrates advantages over traditional logistic regression models in predicting adult sepsis prognosis. The RF model holds significant potential for clinical surveillance and interventions to enhance outcomes for sepsis patients.

Identification of coagulation-related genes as potential diagnostic biomarkers for pediatric septic shock

This study aimed to identify important clotting associated genes (CRGs) associated with septic shock in children and explore possible important mechanisms of the disease. Five hub genes with diagnostic performance were identified using GEO database and data from literature. These hub genes have strong correlation with immune cells. ceRNA network was constructed to explore potential pathogenic mechanisms. Ten candidate small molecule compounds were identified. In summary, the hub genes may play an important role in the immunity and disease development of septic shock, providing new ideas and strategies for future diagnosis and mechanism evaluation of children with septic shock.

The Combination of Systemic Immune-Inflammation Index and Serum Procalcitonin has High Auxiliary Predictive Value for Short-Term Adverse Prognosis in Septic Shock Patients

BACKGROUND

Septic shock is the most serious complication of sepsis, with more secure and efficient biomarkers urgently needed. Systemic immune-inflammation index (SII) and serum procalcitonin (PCT) show involvement in predicting septic shock prognosis.

OBJECTIVE

Herein, we explored the clinical value of the SII-PCT combination in the short-term prognosis of septic shock patients.

METHODS

Totally 200 septic shock patients were analyzed retrospectively and allocated into the survival and death groups upon 28-day in-hospital outcomes. Correlations of SII, PCT, acute physiology and chronic health evaluation II (APACHE II)/sepsis-related organ failure assessment (SOFA) scores, C-reactive protein (CRP), and serum creatinine (Scr) were analyzed using Spearman. The influencing factors of SII and serum PCT for short-term poor prognosis were analyzed using logistic multivariate regression model. The auxiliary predictive value of SII, PCT, and their combination for short-term adverse septic shock prognosis was evaluated by the receiver operating characteristic curve. Differences in the area under the curve (AUC) were compared using MedCalc.

RESULTS

The death group had higher APACHE II/SOFA scores, LYM, CRP, Scr, SII, and PCT levels than the survival group. SII and PCT were positively correlated with APACHE II and SOFA scores, LYM, CRP, and Scr, and were independent risk factors influencing the adverse septic shock prognosis. The AUC of the SII-PCT combination in predicting short-term adverse septic shock prognosis was 0.893 (0.841-0.932), with 76.12% sensitivity and 87.97% specificity, with the combination showing a higher AUC than SII/PCT alone.

CONCLUSIONS

The SII-PCT combination helps predict the adverse prognosis of septic shock patients.

Can We Improve Mortality Prediction in Patients with Sepsis in the Emergency Department?

Background and Objectives: Sepsis represents a global health challenge and requires advanced diagnostic and prognostic approaches due to its elevated rate of morbidity and fatality. Our study aimed to assess the value of a novel set of six biomarkers combined with severity scores in predicting 28 day mortality among patients presenting with sepsis in the Emergency Department (ED). Materials and Methods: This single-center, observational, prospective cohort included sixty-seven consecutive patients with septic shock and sepsis enrolled from November 2020 to December 2022, categorized into survival and non-survival groups based on outcomes. The following were assessed: procalcitonin (PCT), soluble Triggering Receptor Expressed on Myeloid Cells-1 (sTREM-1), the soluble form of the urokinase plasminogen activator receptor (suPAR), high-sensitivity C-reactive protein (hs-CRP), interleukin-6 (IL-6), and azurocidin 1 (AZU1), alongside clinical scores such as the Quick Sequential Organ Failure Assessment (qSOFA), Systemic Inflammatory Response Syndrome (SIRS), the Sequential Organ Failure Assessment (SOFA), the Acute Physiology and Chronic Health Evaluation II (APACHE II), the Simplified Acute Physiology Score II and III (SAPS II/III), the National Early Warning Score (NEWS), Mortality in Emergency Department Sepsis (MEDS), the Charlson Comorbidity Index (CCI), and the Glasgow Coma Scale (GCS). The ability of each biomarker and clinical score and their combinations to predict 28 day mortality were evaluated. Results: The overall mortality was 49.25%. Mechanical ventilation was associated with a higher mortality rate. The levels of IL-6 were significantly higher in the non-survival group and had higher AUC values compared to the other biomarkers. The GCS, SOFA, APACHEII, and SAPS II/III showed superior predictive ability. Combining IL-6 with suPAR, AZU1, and clinical scores SOFA, APACHE II, and SAPS II enhanced prediction accuracy compared with individual biomarkers. Conclusion: In our study, IL-6 and SAPS II/III were the most accurate predictors of 28 day mortality for sepsis patients in the ED.

Outcomes and prognosis of postpartum hemorrhage according to management protocol: an 11-year retrospective study from two referral centers

BACKGROUND

No standard treatment guidelines have been established for postpartum hemorrhage (PPH). We aimed to assess the differences in outcomes and prognoses between patients with PPH who underwent surgical and non-surgical treatment.

METHODS

This retrospective study included 230 patients diagnosed with PPH at two referral hospitals between August 2013 and October 2023. The patients were divided into non-surgical (group 1, n = 159) and surgical intervention groups (group 2, n = 71). A subgroup analysis was performed by dividing the surgical intervention group into immediate (n = 45) and delayed surgical intervention groups (n = 26).

RESULTS

Initial lactic acid levels and shock index were significantly higher in group 2 (2.85 ± 1.37 vs. 4.54 ± 3.63 mmol/L, p = 0.001, and 0.83 ± 0.26 vs. 1.10 ± 0.51, p < 0.001, respectively). Conversely, initial heart rate and body temperature were significantly lower in group 2 (92.5 ± 21.0 vs. 109.0 ± 28.1 beat/min, p < 0.001, and 37.3 ± 0.8 °C vs. 37.0 ± 0.9 °C, p = 0.011, respectively). Logistic regression analysis identified low initial body temperature, high lactic acid level, and shock index as independent predictors of surgical intervention (p = 0.029, p = 0.027, and p = 0.049, respectively). Regarding the causes of PPH, tone was significantly more prevalent in group 1 (57.2% vs. 35.2%, p = 0.002), whereas trauma was significantly more prevalent in group 2 (24.5% vs. 39.4%, p = 0.030). Group 2 had worse overall outcomes and prognoses than group 1. The subgroup analysis showed significantly higher rates of uterine atony combined with other causes, hysterectomy, and disseminated intravascular coagulopathy in the delayed surgical intervention group than the immediate surgical intervention group (42.2% vs. 69.2%, p = 0.027; 51.1% vs. 73.1%, p = 0.049; and 17.8% vs. 46.2%, p = 0.018, respectively).

CONCLUSIONS

Patients with PPH presenting with increased lactic acid levels and shock index and decreased body temperature may be surgical candidates. Additionally, immediate surgical intervention in patients with uterine atony combined with other causes of PPH could improve prognosis and reduce postoperative complications.

Monocytic myeloid-derived suppressor cells as an immune indicator of early diagnosis and prognosis in patients with sepsis

BACKGROUND

Immunosuppression is a leading cause of septic death. Therefore, it is necessary to search for biomarkers that can evaluate the immune status of patients with sepsis. We assessed the diagnostic and prognostic value of low-density neutrophils (LDNs) and myeloid-derived suppressor cells (MDSCs) subsets in the peripheral blood mononuclear cells (PBMCs) of patients with sepsis.

METHODS

LDNs and MDSC subsets were compared among 52 inpatients with sepsis, 33 inpatients with infection, and 32 healthy controls to investigate their potential as immune indicators of sepsis. The percentages of LDNs, monocytic MDSCs (M-MDSCs), and polymorphonuclear MDSCs (PMN-MDSCs) in PBMCs were analyzed. Sequential organ failure assessment (SOFA) scores, C-reactive protein (CRP), and procalcitonin (PCT) levels were measured concurrently.

RESULTS

The percentages of LDNs and MDSC subsets were significantly increased in infection and sepsis as compared to control. MDSCs performed similarly to CRP and PCT in diagnosing infection or sepsis. LDNs and MDSC subsets positively correlated with PCT and CRP levels and showed an upward trend with the number of dysfunctional organs and SOFA score. Non-survivors had elevated M-MDSCs compared with that of patients who survived sepsis within 28 days after enrollment.

CONCLUSIONS

MDSCs show potential as a diagnostic biomarker comparable to CRP and PCT, in infection and sepsis, even in distinguishing sepsis from infection. M-MDSCs show potential as a prognostic biomarker of sepsis and may be useful to predict 28-day hospital mortality in patients with sepsis.

Predictive value of thrombocytopenia for bloodstream infection in patients with sepsis and septic shock

BACKGROUND

Thrombocytopenia is common in patients with sepsis and septic shock.

AIM

To analyse the decrease in the number of platelets for predicting bloodstream infection in patients with sepsis and septic shock in the intensive care unit.

METHODS

A retrospective analysis of patients admitted with sepsis and septic shock in Xingtai People Hospital was revisited. Patient population characteristics and laboratory data were collected for analysis.

RESULTS

The study group consisted of 85 (39%) inpatients with bloodstream infection, and the control group consisted of 133 (61%) with negative results or contamination. The percentage decline in platelet counts (PPCs) in patients positive for pathogens [57.1 (41.3-74.6)] was distinctly higher than that in the control group [18.2 (5.1-43.1)] (P < 0.001), whereas the PPCs were not significantly different among those with gram-positive bacteraemia, gram-negative bacteraemia, and fungal infection. Using receiver operating characteristic curves, the area under the curve of the platelet drop rate was 0.839 (95%CI: 0.783-0.895).

CONCLUSION

The percentage decline in platelet counts is sensitive in predicting bloodstream infection in patients with sepsis and septic shock. However, it cannot identify gram-positive bacteraemia, gram-negative bacteraemia, and fungal infection.