Evidence map›Paper›PMID 41618258›Full record

ArticleBMC medical informatics and decision making2026

Timing matters: a machine learning-driven comparison of community and hospital-onset sepsis.

Ritchie Verma, Ajit Elhance, Trisha J Marsh, Robin L Baudier, Scott P Sherry, Raju Reddy, Nehan Sher, Mohammad Adibuzzaman, Vishnu Mohan, Akram Khan

Abstract readComparative Study
PubMed Full text at PMC Publisher
In one paragraph

Article in BMC medical informatics and decision making, 2026. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Not yet cited in PubMed.

0numbers the graph read from it
0cells of the map it votes in
0citing papers in PubMed
–field-weighted citation impact
1 · What the graph read from it

What it found

Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.

The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.

2 · The registry

The trial behind it

Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.

Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.

3 · Its place in the literature

Who cites it

0 citing papers in PubMed.

No citing paper in PubMed yet.

4 · The record

Corrections and comments

PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.

5 · Who and what money

Authors and funding

10 authors.

Ritchie VermaDivision of Informatics, Clinical Epidemiology and Translational Data Science, Oregon Health & Science University (DICE), Portland, OR, USA.
Ajit ElhanceSchool of Medicine, Oregon Health & Science University, Portland, OR, USA.
Trisha J MarshCenter for Health Systems Effectiveness, Oregon Health & Science University, Portland, OR, USA.
Robin L BaudierBiostatistics & Design Program, Oregon Health & Science University, Portland, OR, USA.
Scott P SherryOregon Health & Science University, Portland, OR, USA.
Raju ReddyDivision of Pulmonary, Department of Medicine, Allergy and Critical Care Medicine, Oregon Health & Science University, Portland, OR, USA.
Nehan SherDivision of Pulmonary, Critical Care and Sleep Medicine, University of Arizona College of Medicine, Phoenix, AZ, USA.
Mohammad AdibuzzamanDepartment of Medicine, Division of Informatics, Clinical Epidemiology and Translational Data Science (DICE), Oregon Health & Science University, Portland, OR, USA.
Vishnu MohanDivision of Informatics, Clinical Epidemiology, and Translational Data Science (DICE), Division of General Internal Medicine and Geriatrics, Department of Medicine, Oregon Health & Science University, Portland, OR, USA.
Akram KhanDivision of Pulmonary, Department of Medicine, Allergy and Critical Care Medicine, Oregon Health & Science University, 3181 SW Sam Jackson Park Road, UHN-67, Portland, OR, 97239, USA. khana@ohsu.edu.ORCID 0000-0003-3091-632X

Funding

No grant is acknowledged in the PubMed record.

6 · The paper itself

Abstract

backgroundSepsis is a leading cause of morbidity and mortality in hospitalized patients. While most sepsis research has focused on community-onset sepsis (COS), hospital-onset sepsis (HOS) is increasingly recognized as a distinct clinical entity with worse outcomes. However, a few studies have systematically compared the characteristics and outcomes of COS and HOS. Understand the differences between COS and HOS from a clinical perspective and study hospital outcomes in sepsis patients using a machine learning driven approach.

methodsWe conducted a retrospective analysis of sepsis events at a major academic medical center in the Pacific Northwest using our institutional and Vizient databases. Adults (≥ 18 years) hospitalized with sepsis between January 2019 and August 2023 were included. We compared demographics, clinical characteristics, comorbidities, and outcomes between COS and HOS. We analyzed the association between the timing of sepsis onset and hospital outcomes. Random Forest models were used to evaluate the variable importance to hospital outcomes.

resultsAmong 2,589 hospitalizations of patients with sepsis in the combined dataset, HOS was associated with significantly higher in-hospital mortality (38.2% vs. 28.5%, P < 0.001), longer median hospital (24 vs. 11 days, P < 0.001), and Intensive Care Unit (7 vs. 2 days, P < 0.001) length of stay (LOS) compared to COS. Patients with HOS also had a higher comorbidity burden and were less likely to receive early antibiotic therapy. In a random forest model, the timing of sepsis onset (HOS vs. COS) emerged as one of the key predictors of both mortality and hospital LOS.

conclusionHOS sepsis is associated with significantly higher mortality, longer hospital and ICU stays, and delayed antibiotic initiation compared to COS. These findings underscore the importance of early recognition and targeted management strategies for HOS. Our insights could also help refine predictive models for better sepsis detection, treatment and prognostication.

Indexed as

Community-Acquired InfectionsHospital MortalityMachine LearningSepsisAgedFemaleHumansLength of StayMaleMiddle AgedRandom ForestRetrospective StudiesTime FactorsCommunity-onset sepsisCritical care outcomesHospital-onset sepsisIntensive care unitsMachine learningRisk factors

Identifiers

PMID41618258
PMCPMC12933990

What OpenQuestion holds

Textmetadata
LicenceCC BY-NC-ND
Read underepoch 390

Registered trials

None linked

Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.