The leap to ordinal: Detailed functional prognosis after traumatic brain injury with a flexible modelling approach.
View / Open Files
Authors
Milosevic, Ioan
Stevens, Robert D
Steyerberg, Ewout W
Nelson, David W
CENTER-TBI investigators participants
Publication Date
2022Journal Title
PLoS One
ISSN
1932-6203
Publisher
Public Library of Science (PLoS)
Language
en
Type
Article
This Version
VoR
Metadata
Show full item recordCitation
Bhattacharyay, S., Milosevic, I., Wilson, L., Menon, D., Stevens, R. D., Steyerberg, E. W., Nelson, D. W., et al. (2022). The leap to ordinal: Detailed functional prognosis after traumatic brain injury with a flexible modelling approach.. PLoS One https://doi.org/10.1371/journal.pone.0270973
Description
Funder: ZNS - Hannelore Kohl Stiftung; funder-id: http://dx.doi.org/10.13039/501100007731
Funder: One Mind
Funder: Integra LifeSciences; funder-id: http://dx.doi.org/10.13039/100009006
Abstract
When a patient is admitted to the intensive care unit (ICU) after a traumatic brain injury (TBI), an early prognosis is essential for baseline risk adjustment and shared decision making. TBI outcomes are commonly categorised by the Glasgow Outcome Scale-Extended (GOSE) into eight, ordered levels of functional recovery at 6 months after injury. Existing ICU prognostic models predict binary outcomes at a certain threshold of GOSE (e.g., prediction of survival [GOSE > 1]). We aimed to develop ordinal prediction models that concurrently predict probabilities of each GOSE score. From a prospective cohort (n = 1,550, 65 centres) in the ICU stratum of the Collaborative European NeuroTrauma Effectiveness Research in TBI (CENTER-TBI) patient dataset, we extracted all clinical information within 24 hours of ICU admission (1,151 predictors) and 6-month GOSE scores. We analysed the effect of two design elements on ordinal model performance: (1) the baseline predictor set, ranging from a concise set of ten validated predictors to a token-embedded representation of all possible predictors, and (2) the modelling strategy, from ordinal logistic regression to multinomial deep learning. With repeated k-fold cross-validation, we found that expanding the baseline predictor set significantly improved ordinal prediction performance while increasing analytical complexity did not. Half of these gains could be achieved with the addition of eight high-impact predictors to the concise set. At best, ordinal models achieved 0.76 (95% CI: 0.74-0.77) ordinal discrimination ability (ordinal c-index) and 57% (95% CI: 54%- 60%) explanation of ordinal variation in 6-month GOSE (Somers' Dxy). Model performance and the effect of expanding the predictor set decreased at higher GOSE thresholds, indicating the difficulty of predicting better functional outcomes shortly after ICU admission. Our results motivate the search for informative predictors that improve confidence in prognosis of higher GOSE and the development of ordinal dynamic prediction models.
Keywords
Research Article, Research and analysis methods, Physical sciences, Medicine and health sciences, People and places, Computer and information sciences, Biology and life sciences
Sponsorship
European Commission (602150)
EPSRC (EP/T022159/1)
Identifiers
pone-d-22-05175
External DOI: https://doi.org/10.1371/journal.pone.0270973
This record's URL: https://www.repository.cam.ac.uk/handle/1810/338819
Rights
Licence:
http://creativecommons.org/licenses/by/4.0/
Statistics
Total file downloads (since January 2020). For more information on metrics see the
IRUS guide.