Variation in SOFA (Sequential Organ Failure Assessment) Score Performance in Different Infectious States

Predictive Value of Multiple Scoring Systems in the Prognosis of Septic Patients with Different Infection Sites: Analysis of the Medical Information Mart for the Intensive Care IV Database

The heterogeneity nature of sepsis is significantly impacted by the site of infection. This study aims to explore the predictive value of multiple scoring systems in assessing the prognosis of septic patients across different infection sites. Data for this retrospective cohort study were extracted from the Medical Information Mart for Intensive Care IV database (MIMIC-IV) (v2.2). Adult patients meeting the criteria for sepsis 3.0 and admitted to the intensive care unit (ICU) were enrolled. Infection sites included were pneumonia, urinary tract infection (UTI), cellulitis, abdominal infection, and bacteremia. The primary outcome assessed was 28-day mortality. The sequential Organ Failure Assessment (SOFA) score, Oxford Acute Severity of Illness Score (OASIS), and Logistic Organ Dysfunction System (LODS) score were compared. Binomial logistic regression analysis was conducted to evaluate the association between these variables and mortality. Additionally, differences in the area under the curve (AUC) of receiver operating characteristic (ROC) among the scoring systems were analyzed. A total of 4721 patients were included in the analysis. The average 28-day mortality rate was 9.4%. Significant differences were observed in LODS, OASIS, and SOFA scores between the 28-day survival and non-survival groups across different infection sites (p < 0.01). In the pneumonia group and abdominal infection group, both the LODS and OASIS scoring systems emerged as independent risk factors for mortality in septic patients (odds ratio [OR]: 1.165, 95% confidence interval [CI]: 1.109-1.224, p < 0.001; OR: 1.047, 95% CI: 1.028-1.065, p < 0.001) (OR: 1.200, 95% CI: 1.091-1.319, p < 0.001; OR: 1.060, 95% CI: 1.025-1.095, p < 0.001). For patients with UTI, the LODS, OASIS, and SOFA scoring systems were identified as independent risk factors for mortality (OR: 1.142, 95% CI: 1.068-1.220, p < 0.001; OR: 1.062, 95% CI: 1.037-1.087, p < 0.001; OR: 1.146, 95% CI: 1.046-1.255, p = 0.004), with the AUC of LODS score and OASIS significantly higher than that of the SOFA score (p = 0.006). Among patients with cellulitis, the OASIS and SOFA scoring systems were identified as independent risk factors for mortality (OR: 1.055, 95% CI: 1.007-1.106, p = 0.025; OR: 1.187, 95% CI: 1.005-1.403, p = 0.044), with no significant difference in prognosis prediction observed (p = 0.243). In the bacteremia group, the LODS scoring system was identified as an independent risk factor for mortality (OR: 1.165, 95% CI: 1.109-1.224, p < 0.001). The findings suggest that LODS scores offer better prognostic accuracy for predicting the mortality risk in septic patients with pneumonia, abdominal infections, bacteremia, and UTI compared to SOFA scores.

The Clinical Utility of Albumin with Sequential Organ Failure Assessment (SOFA) in Improving 30-Day Mortality Prediction in Patients with Infection in the Emergency Department

BACKGROUND

The Sequential Organ Failure Assessment (SOFA) score is currently the primary prognostic tool used in patients with infections to predict sepsis and mortality, although its predictive role remains debated. Serum albumin values have been recently found to correlate with the severity of sepsis. The purpose of this study is to evaluate the clinical usefulness of albumin dosage on SOFA score prediction in infected patients.

METHODS

This prospective single-centre observational study was performed in 2021. We used the net reclassification improvement (NRI) technique to evaluate the additional prognostic value of serum albumin used together with the SOFA score in infected patients. The discriminatory abilities of the SOFA score alone, of albumin levels alone, and of the albumin levels together with (but not incorporated into) the SOFA score was evaluated by comparing the area under the curve of the corresponding receiver operating characteristic (ROC) curves.

RESULTS

We included 949 patients with an infectious status; 8.9% (84/949) died within 30 days of ED admission. The AUROC for the SOFA score was 0.802 (95% CI: 0.756-0.849) and the albumin level was 0.813 (95% CI: 0.775-0.852). The NRI found that serum albumin improved SOFA score predictions of 30-day mortality by 24.3% (p < 0.001), yielding an AUROC of 0.881 (95% CI: 0.848-0.912; p < 0.001).

CONCLUSIONS

Using serum albumin values together with the SOFA score can improve prognostic prediction in patients with infections evaluated in the ED.

Explainable machine learning using perioperative serial laboratory results to predict postoperative mortality in patients with peritonitis-induced sepsis

Purpose

Sepsis is one of the most common causes of death after surgery. Several conventional scoring systems have been developed to predict the outcome of sepsis; however, their predictive power is insufficient. The present study applies explainable machine-learning algorithms to improve the accuracy of predicting postoperative mortality in patients with sepsis caused by peritonitis.

Methods

We performed a retrospective analysis of data from demographic, clinical, and laboratory analyses, including the delta neutrophil index (DNI), WBC and neutrophil counts, and CRP level. Laboratory data were measured before surgery, 12-36 hours after surgery, and 60-84 hours after surgery. The primary study output was the probability of mortality. The areas under the receiver operating characteristic curves (AUCs) of several machine-learning algorithms using the Sequential Organ Failure Assessment (SOFA) and Simplified Acute Physiology Score (SAPS) 3 models were compared. 'SHapley Additive exPlanations' values were used to indicate the direction of the relationship between a variable and mortality.

Results

The CatBoost model yielded the highest AUC (0.933) for mortality compared to SAPS3 and SOFA (0.860 and 0.867, respectively). Increased DNI on day 3, septic shock, use of norepinephrine therapy, and increased international normalized ratio on day 3 had the greatest impact on the model's prediction of mortality.

Conclusion

Machine-learning algorithms increase the accuracy of predicting postoperative mortality in patients with sepsis caused by peritonitis.

Changing trend of neonatal Ca/P/Mg status in a Chinese population

Background

Calcium (Ca), phosphorus (P), and magnesium (Mg) are essential elements for keeping the body homeostasis. We aimed to investigate the changing trend of serum levels of Ca/P/Mg in neonates.

Methods

We enrolled 82 premature newborns, 173 neonatal sepsis, 50 neonatal hypoglycemia, 254 neonatal jaundice, 43 neonatal haemolytic disease, and 59 healthy controls in our retrospective study. Serum levels of Ca/P/Mg were collected and expressed in quarters. We analysed the association between neonatal disorders and Ca/P/Mg levels (fourth quarter vs. first quarter) using binary logistic regression analysis. Smooth curve analysis was performed to analyze the non-linear association between birthweight/procalcitonin (PCT) and Ca/P levels. Threshold effect analysis was also performed to yield the turning point of birthweight/PCT in their associations with Ca/P levels.

Results

Binary logistic regression analyses showed that neonatal haemolytic disease, hypoglycemia, sepsis, jaundice, and prematurity were all significantly associated with the fourth quarter of Ca level (P<10-4; P<10-4; P<10-4; P=0.001; and P<10-4, respectively). Neonatal hypoglycemia and prematurity were significantly associated with the fourth quarter of P level (P=0.004; and P=0.003, respectively). Neonatal haemolytic disease, hypoglycemia, sepsis, jaundice and prematurity were not associated with Mg level. Birthweight was significantly associated with Ca level before and after the turning point of 3,220 grams. PCT was significantly associated with Ca level before and after the turning point of 16.8 µg/L. Birthweight was significantly associated with P level before the turning point of 2,990 gram. PCT was significantly associated with P level before the turning points of 3.5 and 34.21 µg/L.

Conclusions

Neonatal disorders demonstrated a decreasing trend of serum Ca/P level. A significantly non-linear association was observed between birthweight/PCT and serum Ca/P levels.

Predictors and nomogram of in-hospital mortality in sepsis-induced myocardial injury: a retrospective cohort study

BACKGROUND

Sepsis-induced myocardial injury (SIMI) is a common organ dysfunction and is associated with higher mortality in patients with sepsis. We aim to construct a nomogram prediction model to assess the 28-day mortality in patients with SIMI. .

METHOD

We retrospectively extracted data from Medical Information Mart for Intensive Care (MIMIC-IV) open-source clinical database. SIMI was defined by Troponin T (higher than the 99th percentile of upper reference limit value) and patients with cardiovascular disease were excluded. A prediction model was constructed in the training cohort by backward stepwise Cox proportional hazards regression model. The concordance index (C-index), area under the receiver operating characteristics curve (AUC), net reclassification improvement (NRI), integrated discrimination improvement (IDI), calibration plotting and decision-curve analysis (DCA) were used to evaluate the nomogram.

RESULTS

1312 patients with sepsis were included in this study and 1037 (79%) of them presented with SIMI. The multivariate Cox regression analysis in all septic patients revealed that SIMI was independently associated with 28-day mortality of septic patients. The risk factors of diabetes, Apache II score, mechanical ventilation, vasoactive support, Troponin T and creatinine were included in the model and a nomogram was constructed based on the model. The C-index, AUC, NRI, IDI, calibration plotting and DCA showed that the performance of the nomogram was better than the single SOFA score and Troponin T.

CONCLUSION

SIMI is related to the 28-day mortality of septic patients. The nomogram is a well-performed tool to predict accurately the 28-day mortality in patients with SIMI.

Machine learning models for prediction of invasion Klebsiella pneumoniae liver abscess syndrome in diabetes mellitus: a singled centered retrospective study

OBJECTIVE

This study aimed to develop and validate a machine learning algorithm-based model for predicting invasive Klebsiella pneumoniae liver abscess syndrome(IKPLAS) in diabetes mellitus and compare the performance of different models.

METHODS

The clinical signs and data on the admission of 213 diabetic patients with Klebsiella pneumoniae liver abscesses were collected as variables. The optimal feature variables were screened out, and then Artificial Neural Network, Support Vector Machine, Logistic Regression, Random Forest, K-Nearest Neighbor, Decision Tree, and XGBoost models were established. Finally, the model's prediction performance was evaluated by the ROC curve, sensitivity (recall), specificity, accuracy, precision, F1-score, Average Precision, calibration curve, and DCA curve.

RESULTS

Four features of hemoglobin, platelet, D-dimer, and SOFA score were screened by the recursive elimination method, and seven prediction models were established based on these variables. The AUC (0.969), F1-Score(0.737), Sensitivity(0.875) and AP(0.890) of the SVM model were the highest among the seven models. The KNN model showed the highest specificity (1.000). Except that the XGB and DT models over-estimates the occurrence of IKPLAS risk, the other models' calibration curves are a good fit with the actual observed results. Decision Curve Analysis showed that when the risk threshold was between 0.4 and 0.8, the net rate of intervention of the SVM model was significantly higher than that of other models. In the feature importance ranking, the SOFA score impacted the model significantly.

CONCLUSION

An effective prediction model of invasion Klebsiella pneumoniae liver abscess syndrome in diabetes mellitus could be established by a machine learning algorithm, which had potential application value.

Viral load and disease severity in COVID-19

The relationship between COVID-19 severity and viral load is unknown. Our objective was to assess the association between viral load and disease severity in COVID-19. In this single center observational study of adults with laboratory confirmed SARS-CoV-2, the first positive in-hospital nasopharyngeal swab was used to calculate the log10 copies/ml [log10 copy number (CN)] of SARS-CoV-2. Four categories based on level of care and modified sequential organ failure assessment score (mSOFA) at time of swab were determined. Median log10CN was compared between different levels of care and mSOFA quartiles. Median log10CN was compared in patients who did and did not receive influenza vaccine, and the correlation between log10CN and D-dimer was examined. We found that of 396 patients, 54.3% were male, and 25% had no major comorbidity. Hospital mortality was 15.7%. Median mSOFA was 2 (IQR 0-3). Median log10CN was 5.5 (IQR 3.3-8.0). Median log10CN was highest in non-intubated ICU patients [6.4 (IQR 4.4-8.1)] and lowest in intubated ICU patients [3.6 (IQR 2.6-6.9)] (p value < 0.01). In adjusted analyses, this difference remained significant [mean difference 1.16 (95% CI 0.18-2.14)]. There was no significant difference in log10CN between other groups in the remaining pairwise comparisons. There was no association between median log10CN and mSOFA in either unadjusted or adjusted analyses or between median log10CN in patients with and without influenza immunization. There was no correlation between log10CN and D-dimer. We conclude, in our cohort, we did not find a clear association between viral load and disease severity in COVID-19 patients. Though viral load was higher in non-intubated ICU patients than in intubated ICU patients there were no other significant differences in viral load by disease severity.