mlsanityData to 7 Oct 2026

MANDARIN: Mixture-of-Experts Framework for Dynamic Delirium and Coma Prediction in ICU Patients: Development and Validation of an Acute Brain Dysfunction Prediction Model

arXiv 2503.06059 ↗First posted 8 Mar 2025cs.AI cs.LGcited by 0

On the map: Mixture-of-experts → Medical and biomedical MoE

Abstract (arXiv)

Acute brain dysfunction (ABD) is a common, severe ICU complication, presenting as delirium or coma and leading to prolonged stays, increased mortality, and cognitive decline. Traditional screening tools like the Glasgow Coma Scale (GCS), Confusion Assessment Method (CAM), and Richmond Agitation-Sedation Scale (RASS) rely on intermittent assessments, causing delays and inconsistencies. In this study, we propose MANDARIN (Mixture-of-Experts Framework for Dynamic Delirium and Coma Prediction in ICU Patients), a 1.5M-parameter mixture-of-experts neural network to predict ABD in real-time among ICU patients. The model integrates temporal and static data from the ICU to predict the brain status in the next 12 to 72 hours, using a multi-branch approach to account for current brain status. The MANDARIN model was trained on data from 92,734 patients (132,997 ICU admissions) from 2 hospitals between 2008-2019 and validated externally on data from 11,719 patients (14,519 ICU admissions) from 15 hospitals and prospectively on data from 304 patients (503 ICU admissions) from one hospital in 2021-2024. Three datasets were used: the University of Florida Health (UFH) dataset, the electronic ICU Collaborative Research Database (eICU), and the Medical Information Mart for Intensive Care (MIMIC)-IV dataset. MANDARIN significantly outperforms the baseline neurological assessment scores (GCS, CAM, and RASS) for delirium prediction in both external (AUROC 75.5% CI: 74.2%-76.8% vs 68.3% CI: 66.9%-69.5%) and prospective (AUROC 82.0% CI: 74.8%-89.2% vs 72.7% CI: 65.5%-81.0%) cohorts, as well as for coma prediction (external AUROC 87.3% CI: 85.9%-89.0% vs 72.8% CI: 70.6%-74.9%, and prospective AUROC 93.4% CI: 88.5%-97.9% vs 67.7% CI: 57.7%-76.8%) with a 12-hour lead time. This tool has the potential to assist clinicians in decision-making by continuously monitoring the brain status of patients in the ICU.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Medical and biomedical MoE, one of 12 directions in Mixture-of-experts. Builds on 9 of its 47 references that are in the map. First posted on arXiv 8 Mar 2025.

Builds on

9 of 47 references.

References · 9

  1. 2017Attention Is All You Needcited by 59,932
  2. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,120
  3. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
  4. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  5. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,341
  6. 2024Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Expertscited by 280
  7. 2021Self-Supervised Transformer for Sparse and Irregularly Sampled Multivariate Clinical Time-Seriescited by 96
  8. 2024DeLLiriuM: A large language model for delirium prediction in the ICU using structured EHRcited by 4
  9. 2023APRICOT-Mamba: Acuity Prediction in Intensive Care Unit (ICU): Development and Validation of a Stability, Transitions, and Life-Sustaining Therapies Prediction Modelcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024A multi-cohort study on prediction of acute brain dysfunction states using selective state space models
  2. 2026A Multimodal Deep Learning Framework for Predicting ICU Deterioration: Integrating ECG Waveforms with Clinical Data and Clinician Benchmarking
  3. 2026Standalone LLM and a Pre-specified Agentic Pipeline for Explaining ICU Mortality Predictions: a Feasibility Study on the eICU Demo Dataset
  4. 2025Bridging Graph and State-Space Modeling for Intensive Care Unit Length of Stay Prediction
  5. 2026RealICU: Do LLM Agents Understand Long-Context ICU Data? A Benchmark Beyond Behavior Imitation
  6. 2026Rethinking Large Language Models For Irregular Time Series Classification In Critical Care
  7. 2024Large Language Model Capabilities in Perioperative Risk Prediction and Prognostication
  8. 2026iLENS: Interpretable LLM-Guided Mixture-of-Experts for Neuroimaging Survival Analysis