Progression from nonsevere sepsis—i.e., sepsis without organ failure or shock—to severe sepsis or shock among emergency department (ED) patients has been associated with significant mortality. Early recognition in the ED of those who progress to severe sepsis or shock during their hospital course may improve patient outcomes. We sought to identify clinical, demographic, and laboratory parameters that predict progression to severe sepsis, septic shock, or death within 96 h of ED triage among patients with initial presentation of nonsevere sepsis. This is a retrospective cohort of patients presenting to a single urban academic ED from November 2008 to October 2010. Patients aged 18 years or older who met criteria for sepsis and had a lactate level measured in the ED were included. Patients were excluded if they had any combination of the following: a systolic blood pressure <90 mmHg upon triage, an initial whole blood lactate level ≥4 mmol/L, or one or more of a set of predefined signs of organ dysfunction upon initial assessment. Disease progression was defined as the development of any combination of the aforementioned conditions, initiation of vasopressors, or death within 96 h of ED presentation. Data on predefined potential predictors of disease progression and outcome measures of disease progression were collected by a query of the electronic medical record and via chart review. Logistic regression was used to assess associations of potential predictor variables with a composite outcome measure of sepsis progression to organ failure, hypotension, or death. In this cohort of 582 ED patients with nonsevere sepsis, 108 (18.6 %) experienced disease progression. Initial serum albumin <3.5 mg/dL (OR 4.82; 95 % CI 2.40–9.69; p < 0.01) and a diastolic blood pressure <52 mmHg at ED triage (OR 4.59; 95 % CI 1.57–13.39; p < 0.01) were independently associated with disease progression to severe sepsis or shock within 96 h of ED presentation. There were no deaths within 96 h of ED presentation. In our patient cohort, serum albumin <3.5 g/dL and an ED triage diastolic blood pressure <52 mmHg independently predict early progression to severe sepsis or shock among ED patients with presumed sepsis.
OBJECTIVES: To train a model to predict vasopressor use in ICU patients with sepsis and optimize external performance across hospital systems using domain adaptation, a transfer learning approach. DESIGN: Observational cohort study. SETTING: Two academic medical centers from January 2014 to June 2017. PATIENTS: Data were analyzed from 14,512 patients (9,423 at the development site and 5,089 at the validation site) who were admitted to an ICU and met Center for Medicare and Medicaid Services definition of severe sepsis either before or during the ICU stay. Patients were excluded if they never developed sepsis, if the ICU length of stay was less than 8 hours or more than 20 days or if they developed shock up to the first 4 hours of ICU admission. MEASUREMENTS AND MAIN RESULTS: Forty retrospectively collected features from the electronic medical records of adult ICU patients at the development site (four hospitals) were used as inputs for a neural network Weibull-Cox survival model to derive a prediction tool for future need of vasopressors. Domain adaptation updated parameters to optimize model performance in the validation site (two hospitals), a different healthcare system over 2,000 miles away. The cohorts at both sites were randomly split into training and testing sets (80% and 20%, respectively). When applied to the test set in the development site, the model predicted vasopressor use 4–24 hours in advance with an area under the receiver operator characteristic curve, specificity, and positive predictive value ranging from 0.80 to 0.81, 56.2% to 61.8%, and 5.6% to 12.1%, respectively. Domain adaptation improved performance of the model to predict vasopressor use within 4 hours at the validation site (area under the receiver operator characteristic curve 0.81 [CI, 0.80–0.81] from 0.77 [CI, 0.76–0.77], p < 0.01; specificity 59.7% [CI, 58.9–62.5%] from 49.9% [CI, 49.5–50.7%], p < 0.01; positive predictive value 8.9% [CI, 8.5–9.4%] from 7.3 [7.1–7.4%], p < 0.01). CONCLUSIONS: Domain adaptation improved performance of a model predicting sepsis-associated vasopressor use during external validation.
Objectives: To identify circumstances in which repeated measures of organ failure would improve mortality prediction in ICU patients. Design: Retrospective cohort study, with external validation in a deidentified ICU database. Setting: Eleven ICUs in three university hospitals within an academic healthcare system in 2014. Patients: Adults (18 yr old or older) who satisfied the following criteria: 1) two of four systemic inflammatory response syndrome criteria plus an ordered blood culture, all within 24 hours of hospital admission; and 2) ICU admission for at least 2 calendar days, within 72 hours of emergency department presentation. Intervention: None Measurements and Main Results: Data were collected until death, ICU discharge, or the seventh ICU day, whichever came first. The highest Sequential Organ Failure Assessment score from the ICU admission day (ICU day 1) was included in a multivariable model controlling for other covariates. The worst Sequential Organ Failure Assessment scores from the first 7 days after ICU admission were incrementally added and retained if they obtained statistical significance (p < 0.05). The cohort was divided into seven subcohorts to facilitate statistical comparison using the integrated discriminatory index. Of the 1,290 derivation cohort patients, 83 patients (6.4%) died in the ICU, compared with 949 of the 8,441 patients (11.2%) in the validation cohort. Incremental addition of Sequential Organ Failure Assessment data up to ICU day 5 improved the integrated discriminatory index in the validation cohort. Adding ICU day 6 or 7 Sequential Organ Failure Assessment data did not further improve model performance. Conclusions: Serial organ failure data improve prediction of ICU mortality, but a point exists after which further data no longer improve ICU mortality prediction of early sepsis.
Sepsis is associated with significant mortality and morbidity among critically ill patients admitted to intensive care units and represents a major health challenge globally. Given the significant clinical and biological heterogeneity among patients and the dynamic nature of the host immune response, identifying those at high risk of poor outcomes remains a critical challenge. Here, we performed secondary analysis of publicly available time-series gene-expression datasets from peripheral blood of patients admitted to the intensive care unit to elucidate temporally stable gene-expression markers between sepsis survivors and nonsurvivors. Using a limited set of genes that were determined to be temporally stable, we derived a dynamical model using a Support Vector Machine classifier to accurately predict the mortality of sepsis patients. Our model had robust performance in a test dataset, where patients' transcriptome was sampled at alternate time points, with an area under the curve of 0.89 (95% CI, 0.82–0.96) upon 5-fold cross-validation. We also identified 7 potential biomarkers of sepsis mortality (STAT5A, CX3CR1, LCP1, SNRPG, RPS27L, LSM5, SHCBP1) that require future validation. Pending prospective testing, our model may be used to identify sepsis patients with high risk of mortality accounting for the dynamic nature of the disease and with potential therapeutic implications.
OBJECTIVES: Significant practice variation exists in the amount of resuscitative IV fluid given to patients with sepsis. Current research suggests equipoise between a tightly restrictive or more liberal strategy but data is lacking on a wider range of resuscitation practices. We sought to examine the relationship between a wide range of fluid resuscitation practices and sepsis mortality and then identify the primary driver of this practice variation. DESIGN: Retrospective analysis of the Premier Healthcare Database. SETTING: Six hundred twelve U.S. hospitals. PATIENTS: Patients with sepsis and septic shock admitted from the emergency department to the ICU from January 1, 2016, to December 31, 2019. INTERVENTIONS: The volume of resuscitative IV fluid administered before the end of hospital day- 1 and mortality. MEASUREMENTS AND MAIN RESULTS: In total, 190,682 patients with sepsis and septic shock were included in the analysis. Based upon patient characteristics and illness severity, we predicted that physicians should prescribe patients with sepsis a narrow mean range of IV fluid (95% range, 3.6–4.5 L). Instead, we observed wide variation in the mean IV fluids administered (95% range, 1.7–7.4 L). After splitting the patients into five groups based upon attending physician practice, we observed patients in the moderate group (4.0 L; interquartile range [IQR], 2.4–5.1 L) experienced a 2.5% reduction in risk-adjusted mortality compared with either the very low (1.6 L; IQR, 1.0–2.5 L) or very high (6.1 L; IQR, 4.0–9.0 L) fluid groups p < 0.01). An analysis of within- and between-hospital IV fluid resuscitation practices showed that physician variation within hospitals instead of practice differences between hospitals accounts for the observed variation. CONCLUSIONS: Individual physician practice drives excess variation in the amount of IV fluid given to patients with sepsis. A moderate approach to IV fluid resuscitation is associated with decreased sepsis mortality and should be tested in future randomized controlled trials.