STAPLAg: a convenient early warning score for use in infected patients in the intensive care unit

Zhang, Keji; Lv, Dan; Deng, Yuxiao; Zhu, Changqing; Gao, Yuan; Huang, Yuan; Xu, Xinhui

doi:10.1097/md.0000000000020274

Cited by 6 publications

(7 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hypernatremia can be an independent predictor of poor outcome in septic patients in the ICU, which is similar to some views [38]. However, another study [39] showed the risk of death increased by 71.6% when serum sodium was < 129 mmol/L for patients with sepsis. Lactate and AG are typical metabolic indicators.…”

Section: Discussionsupporting

confidence: 81%

Predicting 30-days mortality for MIMIC-III patients with sepsis-3: a machine learning approach using XGboost

et al. 2020

View full text Add to dashboard Cite

Background Sepsis is a significant cause of mortality in-hospital, especially in ICU patients. Early prediction of sepsis is essential, as prompt and appropriate treatment can improve survival outcomes. Machine learning methods are flexible prediction algorithms with potential advantages over conventional regression and scoring system. The aims of this study were to develop a machine learning approach using XGboost to predict the 30-days mortality for MIMIC-III Patients with sepsis-3 and to determine whether such model performs better than traditional prediction models. Methods Using the MIMIC-III v1.4, we identified patients with sepsis-3. The data was split into two groups based on death or survival within 30 days and variables, selected based on clinical significance and availability by stepwise analysis, were displayed and compared between groups. Three predictive models including conventional logistic regression model, SAPS-II score prediction model and XGBoost algorithm model were constructed by R software. Then, the performances of the three models were tested and compared by AUCs of the receiver operating characteristic curves and decision curve analysis. At last, nomogram and clinical impact curve were used to validate the model. Results A total of 4559 sepsis-3 patients are included in the study, in which, 889 patients were death and 3670 survival within 30 days, respectively. According to the results of AUCs (0.819 [95% CI 0.800–0.838], 0.797 [95% CI 0.781–0.813] and 0.857 [95% CI 0.839–0.876]) and decision curve analysis for the three models, the XGboost model performs best. The risk nomogram and clinical impact curve verify that the XGboost model possesses significant predictive value. Conclusions Using machine learning technique by XGboost, more significant prediction model can be built. This XGboost model may prove clinically useful and assist clinicians in tailoring precise management and therapy for the patients with sepsis-3.

show abstract

Section: Discussionsupporting

confidence: 81%

Predicting 30-days mortality for MIMIC-III patients with sepsis-3: a machine learning approach using XGboost

et al. 2020

View full text Add to dashboard Cite

show abstract

“…It was also confirmed in patients with sepsis and severe COVID-19 [ 29 , 30 ]. The parameters of the predicted score established in the authors’ study in 2020 overlap with these indicators [ 11 ].…”

Section: Discussionmentioning

confidence: 99%

“…Because sepsis is caused by a disordered host response to infection, biomarkers related to immune dysfunction have received attention in the study of sepsis in recent years [ 10 ]. In 2019, the authors established the STAPLAg scoring system, which can be used to predict the occurrence of sepsis and subsequent death using six clinical indicators related to the host’s infection and immune status (sodium concentration, troponin I concentration, albumin [ALB] concentration, platelet count [PTL]/lymphocyte ratio, lactate concentration, and age) [ 11 ]. Still, the model is not perfect and can be improved.…”

Section: Introductionmentioning

confidence: 99%

Predictive value of CD86 for the occurrence of sepsis (Sepsis-3) in patients with infection

lv,

Zhang,

Zhu

et al. 2024

PLoS ONE

Self Cite

View full text Add to dashboard Cite

This prospective observational study explored the predictive value of CD86 in the early diagnosis of sepsis in the emergency department. The primary endpoint was the factors associated with a diagnosis of sepsis. The secondary endpoint was the factors associated with mortality among patients with sepsis. It enrolled inpatients with infection or high clinical suspicion of infection in the emergency department of a tertiary Hospital between September 2019 and June 2021. The patients were divided into the sepsis and non-sepsis groups according to the Sepsis-3 standard. The non-sepsis group included 56 patients, and the sepsis group included 65 patients (19 of whom ultimately died). The multivariable analysis showed that CD86% (odds ratio [OR] = 1.22, 95% confidence interval [CI]: 1.04–1.44, P = 0.015), platelet count (OR = 0.99, 95%CI: 0.986–0.997, P = 0.001), interleukin-10 (OR = 1.01, 95%CI: 1.004–1.025, P = 0.009), and procalcitonin (OR = 1.17, 95%CI: 1.01–1.37, P = 0.043) were independent risk factors for sepsis, while human leukocyte antigen (HLA%) (OR = 0.96, 05%CI: 0.935–0.995, P = 0.022), respiratory rate (OR = 1.16, 95%CI: 1.03–1.30, P = 0.014), and platelet count (OR = 1.01, 95%CI: 1.002–1.016, P = 0.016) were independent risk factors for death in patients with sepsis. The model for sepsis (CD86%, platelets, interleukin-10, and procalcitonin) and the model for death (HLA%, respiratory rate, and platelets) had an area under the curve (AUC) of 0.870 and 0.843, respectively. CD86% in the first 24 h after admission for acute infection was independently associated with the occurrence of sepsis in the emergency department.

show abstract

“…Hypoalbuminemia can lead to weakened immunity and increased susceptibility to infectious diseases, and patients with sepsis have complex pathophysiological conditions, including immune imbalance and disorders of biosynthesis and catabolism [15]. Furthermore, hypoalbuminemia was found to be an independent predictor of fatal sepsis in an intensive care unit, with a 75.2% increase in the mortality rate among patients with serum albumin <2.9 g/dL [16]. Serum albumin levels are associated with the prognosis of pneumonia, severe sepsis, and bacteremia [17,18].…”

Section: Discussionmentioning

confidence: 99%

Risk Factors for Frequent Infections in Patients With Extremely Severe Motor and Intellectual Disabilities

Kusaba¹,

Yasumasu²,

Konishi³

et al. 2023

Cureus

View full text Add to dashboard Cite

Background: At our institution, patients of all ages with extremely severe motor and intellectual disabilities (ESMID) receive comprehensive management similar to intensive care for "extremely ill patients." Some patients with ESMID develop frequent infections that are difficult to manage. The purpose of this study was to identify risk factors for frequent infections in these patients.Methods: Thirty-seven patients with ESMID who were treated for infections at our institution between September 2018 and August 2019 were retrospectively investigated. Frequent infection was defined as three or more episodes of infection and antimicrobial treatment in one year. Infection status and potential risk factors for frequent infections (patient background factors, severity score, hematological parameters, anthropometry index, and parenteral nutritional status) were examined in univariate and multivariate analyses.Results: Frequent infections occurred in 11 of the 37 patients (29.7%) during the study period, including respiratory and urinary tract infections. Univariate and multivariate analyses suggested hypoalbuminemia (p<0.01) and hypertriglyceridemia (p<0.01) were independent risk factors for frequent infections.Conclusions: Hypoalbuminemia and hypertriglyceridemia may be risk factors for frequent infections in patients with ESMID.

show abstract

STAPLAg: a convenient early warning score for use in infected patients in the intensive care unit

Cited by 6 publications

References 29 publications

Predicting 30-days mortality for MIMIC-III patients with sepsis-3: a machine learning approach using XGboost

Predicting 30-days mortality for MIMIC-III patients with sepsis-3: a machine learning approach using XGboost

Predictive value of CD86 for the occurrence of sepsis (Sepsis-3) in patients with infection

Risk Factors for Frequent Infections in Patients With Extremely Severe Motor and Intellectual Disabilities

Contact Info

Product

Resources

About