CoChat
Sign Up
Cited by 33Trauma and Emergency Care StudiesMachine Learning in HealthcareArtificial Intelligence in Healthcare

Machine learning without borders? an adaptable tool to optimize mortality prediction in diverse clinical settings.

Open access
Christie, S. Ariane, Hubbard, Alan E., Callcut, Rachael A., Hameed, Morad, Dissak-Delon, Fanny Nadia, Mekolo, David, Saidou, Arabo, Mefire, Alain Chichom, Nsongoo, Pierre, Dicker, Rochelle A., Cohen, Mitchell Jay, Juillard, Catherine·2018·Journal of Trauma and Acute Care Surgery
DOI 10.1097/ta.0000000000002044PMC PMC6225991
Open this paper in CoChat — free account

Abstract

BACKGROUND: Mortality prediction aids clinical decision making and is necessary for quality improvement initiatives. Validated metrics rely on prespecified variables and often require advanced diagnostics, which are unfeasible in resource-constrained contexts. We hypothesize that machine learning will generate superior mortality prediction in both high-income and low- and middle-income country cohorts. METHODS: SuperLearner, an ensemble machine-learning algorithm, was applied to data from three prospective trauma cohorts: a highest-activation cohort in the United States, a high-volume center cohort in South Africa (SA), and a multicenter registry in Cameroon. Cross-validation was used to assess model discrimination of discharge mortality by site using receiver operating characteristic curves. SuperLearner discrimination was compared with standard scoring methods. Clinical variables driving SuperLearner prediction at each site were evaluated. RESULTS: Data from 28,212 injured patients were used to generate prediction. Discharge mortality was 17%, 1.3%, and 1.7% among US, SA, and Cameroonian cohorts. SuperLearner delivered superior prediction of discharge mortality in the United States (area under the curve [AUC], 94–97%) and vastly superior prediction in Cameroon (AUC, 90–94%) compared with conventional scoring algorithms. It provided similar prediction to standard scores in the SA cohort (AUC, 90–95%). Context-specific variables (partial thromboplastin time in the United States and hospital distance in Cameroon) were prime drivers of predicted mortality in their respective cohorts, whereas severe brain injury predicted mortality across sites. CONCLUSIONS: Machine learning provides excellent discrimination of injury mortality in diverse settings. Unlike traditional scores, data-adaptive methods are well suited to optimizing precise site-specific prediction regardless of diagnostic capabilities or data set inclusion allowing for individualized decision making and expanded access to quality improvement programming. LEVEL OF EVIDENCE: Prognostic and therapeutic, level II and III.

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

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

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

Integrity signals

Registry

Crossref · 10.1097/ta.0000000000002044

Cites

34 of 34 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

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

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

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

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Super Learner ranks candidate algorithms by performance and applies an optimal weight to each, creating ensemble algorithms that can accurately predict transfusion requirements and mortality among trauma patients.

    “To capitalize on this phenomenon, Super Learner ranks a set of candidate algorithms20,28,38,39 by their performance and applies an optimal weight to each, creating ensemble algorithms that can accurately predict transfusion requirements and mortality among trauma patients.20,28,38,39”

    From Artificial Intelligence and Surgical Decision-making. (2020) · cites this paper as [20]

    The Methods (SuperLearner Prediction; page not available) describe evaluating multiple algorithms and using cross-validation to form an optimally weighted ensemble. The Results (SL Discrimination of Mortality; page not available) report accurate mortality prediction in three trauma cohorts. The paper does not report prediction of transfusion requirements. (LLM, conf=0.88)

    Experimental — accuracy not yet measured

Self-check

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

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

Cites

Flagged first, then by citations

Research works printed but not linked: 1

  1. [17]CM B Pattern Recognition And Machine Learning. New York: Springer; 2006. 740 p.

Cited by

Sorted by citations

Related

Authors
Christie, S. A., Hubbard, A. E., Callcut, R. A., Hameed, M., Dissak-Delon, F. N., Mekolo, D., Saidou, A., Mefire, A. C., Nsongoo, P., Dicker, R. A., Cohen, M. J., & Juillard, C.
Affiliations
  • University of British Columbia (CA)
  • University of California, Berkeley (US)
  • University of California, San Francisco (US)
  • University of California, Los Angeles (US)
  • Denver Health Medical Center (US)
ORCID
Venue
Journal of Trauma and Acute Care Surgery
Publisher
Ovid Technologies (Wolters Kluwer Health)
Published
2018-11
Volume
85
Issue
5
Pages
921-927
ISSN
  • 2163-0755 (ISSN-L)
  • 2163-0763
DOI
10.1097/ta.0000000000002044
PMC
PMC6225991
OpenAlex
W2886514323
Cited by
33
References
34
Citations by year
2026: 4 · 2025: 7 · 2024: 3 · 2023: 6 · 2022: 7 · 2021: 4 · 2020: 1 · 2019: 1
FWCI
1.83
Type
journal article
Language
en
Open access
Locations
  • The Journal of Trauma: Injury, Infection, and Critical Care (publishedVersion)
  • PubMed (publishedVersion)
  • PubMed Central (acceptedVersion)
  • eScholarship (California Digital Library) (submittedVersion)
Funders
National Institute of Environmental Health Sciences (K01ES026834)
Topics
  • Health Sciences › Medicine › Emergency Medicine › Trauma and Emergency Care Studies
  • Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
  • Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
Keywords
mortality prediction, super learner, ensemble learning, trauma patients, discharge mortality, resource-limited settings, low- and middle-income countries, prognostic score, model discrimination, activated partial thromboplastin time, distance to hospital, severe brain injury, quality improvement
MeSH terms
Machine Learning, Adult, Cameroon, Developing Countries, Female, Forecasting, Health Services Accessibility, Humans, Male, Middle Aged, Partial Thromboplastin Time, ROC Curve, South Africa, United States, Wounds and Injuries, Developed Countries, Area Under Curve

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