Dataset Information

Validation of a machine learning algorithm for early severe sepsis prediction: a retrospective study predicting severe sepsis up to 48 h in advance using a diverse dataset from 461 US hospitals.

ABSTRACT: BACKGROUND:Severe sepsis and septic shock are among the leading causes of death in the United States and sepsis remains one of the most expensive conditions to diagnose and treat. Accurate early diagnosis and treatment can reduce the risk of adverse patient outcomes, but the efficacy of traditional rule-based screening methods is limited. The purpose of this study was to develop and validate a machine learning algorithm (MLA) for severe sepsis prediction up to 48 h before onset using a diverse patient dataset. METHODS:Retrospective analysis was performed on datasets composed of de-identified electronic health records collected between 2001 and 2017, including 510,497 inpatient and emergency encounters from 461 health centers collected between 2001 and 2015, and 20,647 inpatient and emergency encounters collected in 2017 from a community hospital. MLA performance was compared to commonly used disease severity scoring systems and was evaluated at 0, 4, 6, 12, 24, and 48 h prior to severe sepsis onset. RESULTS:270,438 patients were included in analysis. At time of onset, the MLA demonstrated an AUROC of 0.931 (95% CI 0.914, 0.948) and a diagnostic odds ratio (DOR) of 53.105 on a testing dataset, exceeding MEWS (0.725, P?

SUBMITTER: Burdick H

PROVIDER: S-EPMC7590695 | biostudies-literature | 2020 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Validation of a machine learning algorithm for early severe sepsis prediction: a retrospective study predicting severe sepsis up to 48 h in advance using a diverse dataset from 461 US hospitals.

Burdick Hoyt H Pino Eduardo E Gabel-Comeau Denise D Gu Carol C Roberts Jonathan J Le Sidney S Slote Joseph J Saber Nicholas N Pellegrini Emily E Green-Saxena Abigail A Hoffman Jana J Das Ritankar R

BMC medical informatics and decision making 20201027 1

<h4>Background</h4>Severe sepsis and septic shock are among the leading causes of death in the United States and sepsis remains one of the most expensive conditions to diagnose and treat. Accurate early diagnosis and treatment can reduce the risk of adverse patient outcomes, but the efficacy of traditional rule-based screening methods is limited. The purpose of this study was to develop and validate a machine learning algorithm (MLA) for severe sepsis prediction up to 48 h before onset using a d ...[more]

PMID: 33109167

Similar Datasets

Project description:To compare the prevalence, resource utilization, and mortality for pediatric severe sepsis identified using two established identification strategies.Observational cohort study from 2004 to 2012.Forty-four pediatric hospitals contributing data to the Pediatric Health Information Systems database.Children 18 years old or younger.We identified patients with severe sepsis or septic shock by using two International Classification of Diseases, 9th edition, Clinical Modification-based coding strategies: 1) combinations of International Classification of Diseases, 9th edition, Clinical Modification codes for infection plus organ dysfunction (combination code cohort); 2) International Classification of Diseases, 9th edition, Clinical Modification codes for severe sepsis and septic shock (sepsis code cohort). Outcomes included prevalence of severe sepsis, as well as hospital and ICU length of stay, and mortality. Outcomes were compared between the two cohorts examining aggregate differences over the study period and trends over time. The combination code cohort identified 176,124 hospitalizations (3.1% of all hospitalizations), whereas the sepsis code cohort identified 25,236 hospitalizations (0.45%), a seven-fold difference. Between 2004 and 2012, the prevalence of sepsis increased from 3.7% to 4.4% using the combination code cohort and from 0.4% to 0.7% using the sepsis code cohort (p < 0.001 for trend in each cohort). Length of stay (hospital and ICU) and costs decreased in both cohorts over the study period (p < 0.001). Overall, hospital mortality was higher in the sepsis code cohort than the combination code cohort (21.2% [95% CI, 20.7-21.8] vs 8.2% [95% CI, 8.0-8.3]). Over the 9-year study period, there was an absolute reduction in mortality of 10.9% (p < 0.001) in the sepsis code cohort and 3.8% (p < 0.001) in the combination code cohort.Prevalence of pediatric severe sepsis increased in the studied U.S. children's hospitals over the past 9 years, whereas resource utilization and mortality decreased. Epidemiologic estimates of pediatric severe sepsis varied up to seven-fold depending on the strategy used for case ascertainment.

Project description:In the United States, national efforts to reduce hospital readmissions have been enacted, including the application of substantial insurance reimbursement penalties for hospitals with elevated rates. Readmissions after severe sepsis remain understudied and could possibly signify lapses in care and missed opportunities for intervention. We sought to characterize 7- and 30-day readmission rates following hospital admission for severe sepsis as well as institutional variations in readmission.Retrospective analysis of 345,657 severe sepsis discharges from University HealthSystem Consortium hospitals in 2012.United States.We applied the commonly cited method described by Angus et al for identification of severe sepsis, including only discharges with sepsis present at admission.None.We identified unplanned, all-cause readmissions within 7 and 30 days of discharge using claims-based algorithms. Using mixed-effects logistic regression, we determined factors associated with 30-day readmission. We used risk-standardized readmission rates to assess institutional variations. Among 216,328 eligible severe sepsis discharges, there were 14,932 readmissions within 7 days (6.9%; 95% CI, 6.8-7.0) and 43,092 within 30 days (19.9%; 95% CI, 19.8-20.1). Among those readmitted within 30 days, 66.9% had an infection and 40.3% had severe sepsis at readmission. Patient severity, length of stay, and specific diagnoses were associated with increased odds of 30-day readmission. Observed institutional 7-day readmission rates ranged from 0% to 12.3%, 30-day rates from 3.6% to 29.1%, and 30-day risk-standardized readmission rates from 14.1% to 31.1%. Greater institutional volume, teaching status, trauma services, location in the Northeast, and lower ICU rates were associated with poor risk-standardized readmission rate performance.Severe sepsis readmission places a substantial burden on the healthcare system, with one in 15 and one in five severe sepsis discharges readmitted within 7 and 30 days, respectively. Hospitals and clinicians should be aware of this important sequela of severe sepsis.

Dataset Information

Validation of a machine learning algorithm for early severe sepsis prediction: a retrospective study predicting severe sepsis up to 48 h in advance using a diverse dataset from 461 US hospitals.

Publications

Validation of a machine learning algorithm for early severe sepsis prediction: a retrospective study predicting severe sepsis up to 48 h in advance using a diverse dataset from 461 US hospitals.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets