External validation of dynamic clinical states in acute stroke: transportability and independent rediscovery across 176 hospitals
Abstract
ObjectiveFour dynamic clinical states were identified in the first 72 h of stroke intensive care in one centre. We tested whether this representation transports to an independent multicentre cohort, predicts the next state, and is independently recovered.
Materials and Methods8279 adults in 176 hospitals (eICU-CRD v2.0) contributed 70 630 six-hour windows. Phenotype, dictionaries and eligibility rules were frozen before any state was assigned; the model was applied unchanged and judged against five prespecified criteria. Generalised estimating equations related state to subsequent organ support and ICU death; prediction was assessed against a persistence null at 6, 12 and 24 h; a model was fitted de novo in the strictest scope.
ResultsAll five transportability criteria were met in all four scopes. All nine state-outcome comparisons reproduced the direction of association, with exact rank order for invasive ventilation and ICU death; between-hospital intraclass correlations were 0.012-0.027. States persisted across 90.7% of pairs, so prediction was scored on change: AUROC (95% CI) 0.730 (0.723-0.736) externally, 0.735 (0.721-0.749) internally. Fitted de novo, eICU favoured four by BIC but three by restart reproducibility; neither recovered neurological impairment-low support, the other three matched closely in both (r = 0.962-0.991).
DiscussionThe representation transports and carries forward-looking information but is not fully rediscoverable. The unrecovered state is defined by a combination, not a feature: eICU places its windows consistently but never pairs impairment with absent organ support.
ConclusionThree of four states are strongly supported. Transportability and independent rediscovery are distinct and should be reported separately.
Related
- External validation and cross-center transportability of phenotypic age acceleration and laboratory frailty for postoperative mortality prediction: a dual-center cohort study
- External validation of the Intermountain Risk Scores for postdischarge thrombosis and bleeding in an independent population
- Independent external validation of the foramen magnum meningioma risk score: limited discrimination and overestimation of absolute risk
- Antihypertensive Medication Class and Incident Alzheimers Disease and Related Dementias: External Replication Across Two Independent Healthcare Data Sources-the Vanderbilt EHR Synthetic Derivative and US Medicare Claims
- External validation of the eurolung risk model for morbidity using an institutional database on minimally invasive major lung resections
BibTeX
@misc{p2026external,
title = {{External validation of dynamic clinical states in acute stroke: transportability and independent rediscovery across 176 hospitals}},
author = {P. LEI and Y. XU and Y. ZHANG},
howpublished = {medRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.07.26362407},
url = {https://www.medrxiv.org/content/10.64898/2026.09.07.26362407v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - External validation of dynamic clinical states in acute stroke: transportability and independent rediscovery across 176 hospitals
AU - P. LEI
AU - Y. XU
AU - Y. ZHANG
PY - 2026
DA - 2026/09/07
PB - medRxiv
DO - 10.64898/2026.09.07.26362407
UR - https://www.medrxiv.org/content/10.64898/2026.09.07.26362407v1
AB - ObjectiveFour dynamic clinical states were identified in the first 72 h of stroke intensive care in one centre. We tested whether this representation transports to an independent multicentre cohort, predicts the next state, and is independently recovered. Materials and Methods8279 adults in 176 hospitals (eICU-CRD v2.0) contributed 70 630 six-hour windows. Phenotype, dictionaries and eligibility rules were frozen before any state was assigned; the model was applied unchanged and judged against five prespecified criteria. Generalised estimating equations related state to subsequent organ support and ICU death; prediction was assessed against a persistence null at 6, 12 and 24 h; a model was fitted de novo in the strictest scope. ResultsAll five transportability criteria were met in all four scopes. All nine state-outcome comparisons reproduced the direction of association, with exact rank order for invasive ventilation and ICU death; between-hospital intraclass correlations were 0.012-0.027. States persisted across 90.7% of pairs, so prediction was scored on change: AUROC (95% CI) 0.730 (0.723-0.736) externally, 0.735 (0.721-0.749) internally. Fitted de novo, eICU favoured four by BIC but three by restart reproducibility; neither recovered neurological impairment-low support, the other three matched closely in both (r = 0.962-0.991). DiscussionThe representation transports and carries forward-looking information but is not fully rediscoverable. The unrecovered state is defined by a combination, not a feature: eICU places its windows consistently but never pairs impairment with absent organ support. ConclusionThree of four states are strongly supported. Transportability and independent rediscovery are distinct and should be reported separately.
ER -