FIRST-ICU: Forecasting Interventions and Risk Stratification in the ICU using Graph Neural Network Autoencoders

Aikodon, N, Olier, I ORCID: 0000-0002-5679-7501, Johnston, BW, Welters, ID, Lip, GYH ORCID: 0000-0002-7566-1626 and Ortega-Martorell, S ORCID: 0000-0001-9927-3209 (2026) FIRST-ICU: Forecasting Interventions and Risk Stratification in the ICU using Graph Neural Network Autoencoders. npj Digital Medicine. ISSN 2398-6352

Preview	Text FIRST-ICU- Forecasting Interventions and Risk Stratification in the ICU using Graph Neural Network Autoencoders.pdf - Accepted Version Available under License Creative Commons Attribution. Download (2MB) | Preview
Preview	Text Supplementary Material.pdf - Supplemental Material Available under License Creative Commons Attribution. Download (295kB) | Preview

Abstract

Critically ill patients frequently require multiple concurrent interventions with complex interdependencies, yet existing prediction models treat these as independent events. We developed FIRST-ICU (Forecasting Interventions and Risk Stratification in the ICU), a unified deep learning framework integrating a graph neural network encoder, LSTM, and a novel Intervention Interaction Attention Module (IIAM) for joint prediction of seven ICU interventions. FIRST-ICU was developed using MIMIC-IV (n=23,926) and externally validated on AmsterdamUMCdb (n=12,603) without retraining.
The Temporal Decoder achieved AUC-ROC >0.98 for all interventions with Brier scores <0.035. The Discrete Decoder outperformed state-of-the-art baselines, achieving the highest Macro Average Precision for six of seven interventions. Gains were largest for vasopressor interventions, with norepinephrine and phenylephrine improving by 28.0% and 32.8%, respectively, over CNN baselines. Ablation analysis showed that IIAM improved AUC-PR, particularly for vasopressor prediction. Cold-start analysis confirmed robust prediction from physiological signals alone (AUC-PR 0.667-0.868). External validation maintained AUC-ROC >0.90 across intervention categories despite substantial differences in prescribing practices. A Generative Topographic Mapping layer identified six clinically distinct phenotypes, enabling interpretable risk stratification.
FIRST-ICU advances multi-intervention prediction through joint modelling of treatment co-occurrence patterns, validated physiological learning, cross-continental generalisability, and interpretable risk stratification. It provides a framework for multi-intervention ICU decision support.

Item Type:	Article
Uncontrolled Keywords:	4203 Health services and systems
Subjects:	Q Science > QA Mathematics > QA76 Computer software R Medicine > RT Nursing
Divisions:	Computer Science and Mathematics
Publisher:	Nature
Date of acceptance:	4 June 2026
Date of first compliant Open Access:	17 June 2026
Date Deposited:	04 Jun 2026 11:36
Last Modified:	17 Jun 2026 12:19
DOI or ID number:	10.1038/s41746-026-02890-1
URI:	https://researchonline.ljmu.ac.uk/id/eprint/28732

View Item