skip to main content


Title: Evaluation of Sepsis Prediction Models before Onset of Treatment
BACKGROUND Timely interventions, such as antibiotics and intravenous fluids, have been associated with reduced mortality in patients with sepsis. Artificial intelligence (AI) models that accurately predict risk of sepsis onset could speed the delivery of these interventions. Although sepsis models generally aim to predict its onset, clinicians might recognize and treat sepsis before the sepsis definition is met. Predictions occurring after sepsis is clinically recognized (i.e., after treatment begins) may be of limited utility. Researchers have not previously investigated the accuracy of sepsis risk predictions that are made before treatment begins. Thus, we evaluate the discriminative performance of AI sepsis predictions made throughout a hospitalization relative to the time of treatment. METHODS We used a large retrospective inpatient cohort from the University of Michigan’s academic medical center (2018–2020) to evaluate the Epic sepsis model (ESM). The ability of the model to predict sepsis, both before sepsis criteria are met and before indications of treatment plans for sepsis, was evaluated in terms of the area under the receiver operating characteristic curve (AUROC). Indicators of a treatment plan were identified through electronic data capture and included the receipt of antibiotics, fluids, blood culture, and/or lactate measurement. The definition of sepsis was a composite of the Centers for Disease Control and Prevention’s surveillance criteria and the severe sepsis and septic shock management bundle definition. RESULTS The study included 77,582 hospitalizations. Sepsis occurred in 3766 hospitalizations (4.9%). ESM achieved an AUROC of 0.62 (95% confidence interval [CI], 0.61 to 0.63) when including predictions before sepsis criteria were met and in some cases, after clinical recognition. When excluding predictions after clinical recognition, the AUROC dropped to 0.47 (95% CI, 0.46 to 0.48). CONCLUSIONS We evaluate a sepsis risk prediction model to measure its ability to predict sepsis before clinical recognition. Our work has important implications for future work in model development and evaluation, with the goal of maximizing the clinical utility of these models. (Funded by Cisco Research and others.)  more » « less
Award ID(s):
2124127
PAR ID:
10522981
Author(s) / Creator(s):
; ; ; ; ; ; ;
Publisher / Repository:
Massachusetts Medical Society
Date Published:
Journal Name:
NEJM AI
Volume:
1
Issue:
3
ISSN:
2836-9386
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Sepsis is a life-threatening organ malfunction caused by the host's inability to fight infection, which can lead to death without proper and immediate treatment. Therefore, early diagnosis and medical treatment of sepsis in critically ill populations at high risk for sepsis and sepsis-associated mortality are vital to providing the patient with rapid therapy. Studies show that advancing sepsis detection by 6 hours leads to earlier administration of antibiotics, which is associated with improved mortality. However, clinical scores like Sequential Organ Failure Assessment (SOFA) are not applicable for early prediction, while machine learning algorithms can help capture the progressing pattern for early prediction. Therefore, we aim to develop a machine learning algorithm that predicts sepsis onset 6 hours before it is suspected clinically. Although some machine learning algorithms have been applied to sepsis prediction, many of them did not consider the fact that six hours is not a small gap. To overcome this big gap challenge, we explore a multi-subset approach in which the likelihood of sepsis occurring earlier than 6 hours is output from a previous subset and feed to the target subset as additional features. Moreover, we use the hourly sampled data like vital signs in an observation window to derive a temporal change trend to further assist, which however is often ignored by previous studies. Our empirical study shows that both the multi-subset approach to alleviating the 6-hour gap and the added temporal trend features can help improve the performance of sepsis-related early prediction. 
    more » « less
  2. Background and Objectives: Sepsis is a leading cause of mortality in intensive care units (ICUs). The development of a robust prognostic model utilizing patients’ clinical data could significantly enhance clinicians’ ability to make informed treatment decisions, potentially improving outcomes for septic patients. This study aims to create a novel machine-learning framework for constructing prognostic tools capable of predicting patient survival or mortality outcome. Methods: A novel dataset is created using concatenated triples of static data, temporal data, and clinical outcomes to expand data size. This structured input trains five machine learning classifiers (KNN, Logistic Regression, SVM, RF, and XGBoost) with advanced feature engineering. Models are evaluated on an independent cohort using AUROC and a new metric, 𝛾, which incorporates the F1 score, to assess discriminative power and generalizability. Results: We developed five prognostic models using the concatenated triple dataset with 10 dynamic features from patient medical records. Our analysis shows that the Extreme Gradient Boosting (XGBoost) model (AUROC = 0.777, F1 score = 0.694) and the Random Forest (RF) model (AUROC = 0.769, F1 score = 0.647), when paired with an ensemble under-sampling strategy, outperform other models. The RF model improves AUROC by 6.66% and reduces overfitting by 54.96%, while the XGBoost model shows a 0.52% increase in AUROC and a 77.72% reduction in overfitting. These results highlight our framework’s ability to enhance predictive accuracy and generalizability, particularly in sepsis prognosis. Conclusion: This study presents a novel modeling framework for predicting treatment outcomes in septic patients, designed for small, imbalanced, and high-dimensional datasets. By using temporal feature encoding, advanced sampling, and dimension reduction techniques, our approach enhances standard classifier performance. The resulting models show improved accuracy with limited data, offering valuable prognostic tools for sepsis management. This framework demonstrates the potential of machine learning in small medical datasets. 
    more » « less
  3. Abstract Background Sepsis is a heterogeneous syndrome, and the identification of clinical subphenotypes is essential. Although organ dysfunction is a defining element of sepsis, subphenotypes of differential trajectory are not well studied. We sought to identify distinct Sequential Organ Failure Assessment (SOFA) score trajectory-based subphenotypes in sepsis. Methods We created 72-h SOFA score trajectories in patients with sepsis from four diverse intensive care unit (ICU) cohorts. We then used dynamic time warping (DTW) to compute heterogeneous SOFA trajectory similarities and hierarchical agglomerative clustering (HAC) to identify trajectory-based subphenotypes. Patient characteristics were compared between subphenotypes and a random forest model was developed to predict subphenotype membership at 6 and 24 h after being admitted to the ICU. The model was tested on three validation cohorts. Sensitivity analyses were performed with alternative clustering methodologies. Results A total of 4678, 3665, 12,282, and 4804 unique sepsis patients were included in development and three validation cohorts, respectively. Four subphenotypes were identified in the development cohort: Rapidly Worsening ( n  = 612, 13.1%), Delayed Worsening ( n  = 960, 20.5%), Rapidly Improving ( n  = 1932, 41.3%), and Delayed Improving ( n  = 1174, 25.1%). Baseline characteristics, including the pattern of organ dysfunction, varied between subphenotypes. Rapidly Worsening was defined by a higher comorbidity burden, acidosis, and visceral organ dysfunction. Rapidly Improving was defined by vasopressor use without acidosis. Outcomes differed across the subphenotypes, Rapidly Worsening had the highest in-hospital mortality (28.3%, P -value < 0.001), despite a lower SOFA (mean: 4.5) at ICU admission compared to Rapidly Improving (mortality:5.5%, mean SOFA: 5.5). An overall prediction accuracy of 0.78 (95% CI, [0.77, 0.8]) was obtained at 6 h after ICU admission, which increased to 0.87 (95% CI, [0.86, 0.88]) at 24 h. Similar subphenotypes were replicated in three validation cohorts. The majority of patients with sepsis have an improving phenotype with a lower mortality risk; however, they make up over 20% of all deaths due to their larger numbers. Conclusions Four novel, clinically-defined, trajectory-based sepsis subphenotypes were identified and validated. Identifying trajectory-based subphenotypes has immediate implications for the powering and predictive enrichment of clinical trials. Understanding the pathophysiology of these differential trajectories may reveal unanticipated therapeutic targets and identify more precise populations and endpoints for clinical trials. 
    more » « less
  4. Abstract

    Septic shock is a life-threatening condition in which timely treatment substantially reduces mortality. Reliable identification of patients with sepsis who are at elevated risk of developing septic shock therefore has the potential to save lives by opening an early window of intervention. We hypothesize the existence of a novel clinical state of sepsis referred to as the “pre-shock” state, and that patients with sepsis who enter this state are highly likely to develop septic shock at some future time. We apply three different machine learning techniques to the electronic health record data of 15,930 patients in the MIMIC-III database to test this hypothesis. This novel paradigm yields improved performance in identifying patients with sepsis who will progress to septic shock, as defined by Sepsis- 3 criteria, with the best method achieving a 0.93 area under the receiver operating curve, 88% sensitivity, 84% specificity, and median early warning time of 7 hours. Additionally, we introduce the notion of patient-specific positive predictive value, assigning confidence to individual predictions, and achieving values as high as 91%. This study demonstrates that early prediction of impending septic shock, and thus early intervention, is possible many hours in advance.

     
    more » « less
  5. Introduction Studies have reported that antidiabetic medications (ADMs) were associated with lower risk of dementia, but current findings are inconsistent. This study compared the risk of dementia onset in patients with type 2 diabetes (T2D) treated with sulfonylurea (SU) or thiazolidinedione (TZD) to patients with T2D treated with metformin (MET). Research design and methods This is a prospective observational study within a T2D population using electronic medical records from all sites of the Veterans Affairs Healthcare System. Patients with T2D who initiated ADM from January 1, 2001, to December 31, 2017, were aged ≥60 years at the initiation, and were dementia-free were identified. A SU monotherapy group, a TZD monotherapy group, and a control group (MET monotherapy) were assembled based on prescription records. Participants were required to take the assigned treatment for at least 1 year. The primary outcome was all-cause dementia, and the two secondary outcomes were Alzheimer’s disease and vascular dementia, defined by International Classification of Diseases (ICD), 9th Revision, or ICD, 10th Revision, codes. The risks of developing outcomes were compared using propensity score weighted Cox proportional hazard models. Results Among 559 106 eligible veterans (mean age 65.7 (SD 8.7) years), the all-cause dementia rate was 8.2 cases per 1000 person-years (95% CI 6.0 to 13.7). After at least 1 year of treatment, TZD monotherapy was associated with a 22% lower risk of all-cause dementia onset (HR 0.78, 95% CI 0.75 to 0.81), compared with MET monotherapy, and 11% lower for MET and TZD dual therapy (HR 0.89, 95% CI 0.86 to 0.93), whereas the risk was 12% higher for SU monotherapy (HR 1.12 95% CI 1.09 to 1.15). Conclusions Among patients with T2D, TZD use was associated with a lower risk of dementia, and SU use was associated with a higher risk compared with MET use. Supplementing SU with either MET or TZD may partially offset its prodementia effects. These findings may help inform medication selection for elderly patients with T2D at high risk of dementia. 
    more » « less