CoChat

A Machine Learning Sepsis Prediction Algorithm for Intended Intensive Care Unit Use (NAVOY Sepsis): Proof-of-Concept Study

Open access

Published version of a preprint

The DOI matches its Crossref record; 34 of the 34 references it cites were found in a registry or an index.

Abstract

Background: Despite decades of research, sepsis remains a leading cause of mortality and morbidity in intensive care units worldwide. The key to effective management and patient outcome is early detection, for which no prospectively validated machine learning prediction algorithm is currently available for clinical use in Europe. Objective: We aimed to develop a high-performance machine learning sepsis prediction algorithm based on routinely collected intensive care unit data, designed to be implemented in European intensive care units. Methods: The machine learning algorithm was developed using convolutional neural networks, based on Massachusetts Institute of Technology Lab for Computational Physiology MIMIC-III clinical data from intensive care unit patients aged 18 years or older. The model uses 20 variables to produce hourly predictions of onset of sepsis, defined by international Sepsis-3 criteria. Predictive performance was externally validated using hold-out test data. Results: The algorithm—NAVOY Sepsis—uses 4 hours of input and can identify patients with high risk of developing sepsis, with high performance (area under the receiver operating characteristics curve 0.90; area under the precision-recall curve 0.62) for predictions up to 3 hours before sepsis onset. Conclusions: The prediction performance of NAVOY Sepsis was superior to that of existing sepsis early warning scoring systems and comparable with those of other prediction algorithms designed to predict sepsis onset. The algorithm has excellent predictive properties and uses variables that are routinely collected in intensive care units.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.2196/28000

Cites

34 of 34 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 Intensive care unit (ICU) stays included in the analyses. EHR: electronic health record; ICD-9: International Statistical Classification of Disease, ninth revision.
Figure 1 Intensive care unit (ICU) stays included in the analyses. EHR: electronic health record; ICD-9: International Statistical Classification of Disease, ninth revision.CC BY · PubMed Central
Figure 2 Receiver operating characteristics curve of the algorithm for (A) training data and (B) hold-out test data predictions 3 hours before sepsis onset. AUROC: area under the receiver operating characteristics curve; FPR: false positive rate; TPR: true positive rate.
Figure 2 Receiver operating characteristics curve of the algorithm for (A) training data and (B) hold-out test data predictions 3 hours before sepsis onset. AUROC: area under the receiver operating characteristics curve; FPR: false positive rate; TPR: true positive rate.CC BY · PubMed Central
Figure 3 (A) AUROC and (B) AUPRC for comparison risk scores for sepsis predictions up to 3 hours in advance. AUPRC: area under the precision-recall curve; AUROC: area under the receiver operating characteristics curve; MEWS: Modified Early Warning Score; NEWS2: National Early Warning Score 2; PRESEP: Prehospital Early Sepsis Detection; qSOFA: Quick Sepsis-Related Organ Failure Assessment; RETTS: Rapid Emergency Triage and Treatment System; SIRS: Systemic Inflammatory Response Syndrome; SOFA: Sepsis-Related Organ Failure Assessment.
Figure 3 (A) AUROC and (B) AUPRC for comparison risk scores for sepsis predictions up to 3 hours in advance. AUPRC: area under the precision-recall curve; AUROC: area under the receiver operating characteristics curve; MEWS: Modified Early Warning Score; NEWS2: National Early Warning Score 2; PRESEP: Prehospital Early Sepsis Detection; qSOFA: Quick Sepsis-Related Organ Failure Assessment; RETTS: Rapid Emergency Triage and Treatment System; SIRS: Systemic Inflammatory Response Syndrome; SOFA: Sepsis-Related Organ Failure Assessment.CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 34 references

Research works printed but not linked: 4

  1. AbadiMBarhamPChenJTensorFlow: a system for large-scale machine learningProceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI ’16)201612th USENIX Symposium on Operating Systems Design and Implementation (OSDI ’16)November 2-4Savannah, GA, USA265283
  2. 2017, Updated Report of a Working Party
  3. Moor, M, 2019, Proc Mach Learn Res, 106, 2
  4. Futoma, J, 2017, Proc Mach Learn Res, 68, 243

Cited by

See all 59

Metadata

Authors
Persson, I., Östling, A., Arlbrandt, M., Söderberg, J., & Becedas, D.
Affiliations
  • Uppsala University (SE)
  • Stockholm South General Hospital (SE)
Corresponding author
Persson, Inger
Venue
JMIR Formative Research
Published
2021-09-30
Volume
5
Issue
9
Pages
e28000
ISSN
2561-326X (ISSN-L)
OpenAlex
W3193078598
Cited by
58
References
34
Citations by year
2026: 13 · 2025: 14 · 2024: 13 · 2023: 11 · 2022: 7
FWCI
5.58
Type
journal article
Language
en
Open access
Licence
cc-by
Locations
  • JMIR Formative Research (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • KTH Publication Database DiVA (KTH Royal Institute of Technology) (submittedVersion, other-oa)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
Funders
  • Uppsala Universitet
  • Skånes universitetssjukhus
Topics
  • Health Sciences › Medicine › Critical Care and Intensive Care Medicine › Sepsis Diagnosis and Treatment
  • Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
  • Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
Keywords
sepsis prediction, early sepsis detection, intensive care unit, convolutional neural networks, MIMIC-III, Sepsis-3 criteria, early warning scores, clinical decision support, routinely collected clinical data

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.