Format

Send to

Choose Destination
BMJ Open. 2018 Jan 26;8(1):e017833. doi: 10.1136/bmjopen-2017-017833.

Multicentre validation of a sepsis prediction algorithm using only vital sign data in the emergency department, general ward and ICU.

Author information

1
Dascena Inc., Hayward, California, USA.
2
Department of Emergency Medicine, University of California San Francisco, San Francisco, California, USA.
3
Department of Anesthesia and Perioperative Care, University of California San Francisco, San Francisco, California, USA.
4
Department of Medicine, Stanford University School of Medicine, Stanford, California, USA.
5
Kaiser Permanente South San Francisco Medical Center, South San Francisco, California, USA.
6
Division of Internal Medicine, University of Washington School of Medicine, Seattle, Washington, USA.
7
Department of Clinical Informatics, Stanford University School of Medicine, Stanford, California, USA.
8
Department of Emergency Medicine, Kaiser Permanente Redwood City Medical Center, Redwood City, California, USA.
9
Department of Statistics, University of California Berkeley, Berkeley, California, USA.

Abstract

OBJECTIVES:

We validate a machine learning-based sepsis-prediction algorithm (InSight) for the detection and prediction of three sepsis-related gold standards, using only six vital signs. We evaluate robustness to missing data, customisation to site-specific data using transfer learning and generalisability to new settings.

DESIGN:

A machine-learning algorithm with gradient tree boosting. Features for prediction were created from combinations of six vital sign measurements and their changes over time.

SETTING:

A mixed-ward retrospective dataset from the University of California, San Francisco (UCSF) Medical Center (San Francisco, California, USA) as the primary source, an intensive care unit dataset from the Beth Israel Deaconess Medical Center (Boston, Massachusetts, USA) as a transfer-learning source and four additional institutions' datasets to evaluate generalisability.

PARTICIPANTS:

684 443 total encounters, with 90 353 encounters from June 2011 to March 2016 at UCSF.

INTERVENTIONS:

None.

PRIMARY AND SECONDARY OUTCOME MEASURES:

Area under the receiver operating characteristic (AUROC) curve for detection and prediction of sepsis, severe sepsis and septic shock.

RESULTS:

For detection of sepsis and severe sepsis, InSight achieves an AUROC curve of 0.92 (95% CI 0.90 to 0.93) and 0.87 (95% CI 0.86 to 0.88), respectively. Four hours before onset, InSight predicts septic shock with an AUROC of 0.96 (95% CI 0.94 to 0.98) and severe sepsis with an AUROC of 0.85 (95% CI 0.79 to 0.91).

CONCLUSIONS:

InSight outperforms existing sepsis scoring systems in identifying and predicting sepsis, severe sepsis and septic shock. This is the first sepsis screening system to exceed an AUROC of 0.90 using only vital sign inputs. InSight is robust to missing data, can be customised to novel hospital data using a small fraction of site data and retains strong discrimination across all institutions.

KEYWORDS:

Clinical Decision Support; Electronic Health Records; Machine Learning; Prediction; Sepsis; Septic Shock

PMID:
29374661
PMCID:
PMC5829820
DOI:
10.1136/bmjopen-2017-017833
[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for HighWire Icon for PubMed Central
Loading ...
Support Center