Introduction Patients with sepsis who present to an emergency department (ED) have highly variable underlying disease severity, and can be categorized from low to high risk. Development of a risk stratification tool for these patients is important for appropriate triage and early treatment. The aim of this study was to develop machine learning models predicting 31-day mortality in patients presenting to the ED with sepsis and to compare these to internal medicine physicians and clinical risk scores. Methods A single-center, retrospective cohort study was conducted amongst 1,344 emergency department patients fulfilling sepsis criteria. Laboratory and clinical data that was available in the first two hours of presentation from these patients were randomly partitioned into a development (n = 1,244) and validation dataset (n = 100). Machine learning models were trained and evaluated on the development dataset and compared to internal medicine physicians and risk scores in the independent validation dataset. The primary outcome was 31-day mortality. Results A number of 1,344 patients were included of whom 174 (13.0%) died. Machine learning models trained with laboratory or a combination of laboratory + clinical data achieved an area-under-the ROC curve of 0.82 (95% CI: 0.80–0.84) and 0.84 (95% CI: 0.81–0.87) for predicting 31-day mortality, respectively. In the validation set, models outperformed internal medicine physicians and clinical risk scores in sensitivity (92% vs. 72% vs. 78%;p<0.001,all comparisons) while retaining comparable specificity (78% vs. 74% vs. 72%;p>0.02). The model had higher diagnostic accuracy with an area-under-the-ROC curve of 0.85 (95%CI: 0.78–0.92) compared to abbMEDS (0.63,0.54–0.73), mREMS (0.63,0.54–0.72) and internal medicine physicians (0.74,0.65–0.82). Conclusion Machine learning models outperformed internal medicine physicians and clinical risk scores in predicting 31-day mortality. These models are a promising tool to aid in risk stratification of patients presenting to the ED with sepsis.
Ambulance patients are seriously ill, but sepsis is often not documented by ambulance staff. Nondocumentation is associated with high mortality and could be resolved by assessing vital signs, particularly the temperature.
IntroductionPatients with sepsis who present to an emergency department (ED) have highly variable underlying disease severity, and can be categorized from low to high risk. Development of a risk stratification tool for these patients is important for appropriate triage and early treatment. The aim of this study was to develop machine learning models predicting 31-day mortality in patients presenting to the ED with sepsis and to compare these to internal medicine physicians and clinical risk scores.MethodsA single-center, retrospective cohort study was conducted amongst 1,344 emergency department patients fulfilling sepsis criteria. Laboratory and clinical data that was available in the first two hours of presentation from these patients were randomly partitioned into a development (n=1,244) and validation dataset (n=100). Machine learning models were trained and evaluated on the development dataset and compared to internal medicine physicians and risk scores in the independent validation dataset. The primary outcome was 31-day mortality.ResultsA number of 1,344 patients were included of whom 174 (13.0%) died. Machine learning models trained with laboratory or a combination of laboratory + clinical data achieved an area-under-the ROC curve of 0.82 (95% CI: 0.80-0.84) and 0.84 (95% CI: 0.81-0.87) for predicting 31-day mortality, respectively. In the validation set, models outperformed internal medicine physicians and clinical risk scores in sensitivity (92% vs. 72% vs. 78%;p<0.001,all comparisons) while retaining comparable specificity (78% vs. 74% vs. 72%;p>0.02). The model had higher diagnostic accuracy with an area-under-the-ROC curve of 0.85 (95%CI: 0.78-0.92) compared to abbMEDS (0.63,0.54-0.73), mREMS (0.63,0.54-0.72) and internal medicine physicians (0.74,0.65-0.82).ConclusionMachine learning models outperformed internal medicine physicians and clinical risk scores in predicting 31-day mortality. These models are a promising tool to aid in risk stratification of patients presenting to the ED with sepsis.
Objectives: To determine the effect of a single dose of gentamicin on the incidence and persistence of acute kidney injury (AKI) in patients with sepsis in the emergency department (ED). Methods: We retrospectively studied patients with sepsis in the ED in three hospitals. Local antibiotic guidelines recommended a single dose of gentamicin as part of empirical therapy in selected patients in one hospital, whereas the other two hospitals did not. Multivariate analysis was used to evaluate the effect of gentamicin and other potential risk factors on the incidence and persistence of AKI after admission. AKI was defined according to the KDIGO (Kidney Disease Improving Global Outcomes) criteria. Results: Of 1573 patients, 571 (32.9%) received a single dose of gentamicin. At admission, 181 (31.7%) of 571 of the gentamicin-treated and 228 (22.8%) of 1002 of the nonegentamicin-treated patients had AKI (p < 0.001). After admission, AKI occurred in 64 (12.0%) of 571 patients who received gentamicin and in 82 (8.9%) of 1002 people in the control group (p 0.06). Multivariate analysis showed that shock (odds ratio (OR), 2.72; 95% CI, 1.31e5.67), diabetes mellitus (OR, 1.49; 95% CI, 1.001e2.23) and higher baseline (i.e. before admission) serum creatinine levels (OR, 1.007; 95% CI, 1.005e1.009) were associated with the development of AKI after admission, but not receipt of gentamicin (OR, 1.29; 95% CI, 0.89e1.86). Persistent AKI was rare in both the group that received gentamicin (16/260, 6.2%) and the group that did not (15/454, 3.3%, p 0.09). Conclusions: With regard to renal function, a single dose of gentamicin in patients with sepsis in the ED is safe. The development of AKI after admission was associated with shock, diabetes mellitus and higher baseline creatinine level.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.