Real-time prediction of intensive care unit patient acuity and therapy requirements using state-space modelling
Intensive care unit (ICU) patients often experience rapid changes in clinical status, requiring timely identification of deterioration to guide life-sustaining interventions. Current artificial intelligence (AI) models for acuity assessment rely on mortality as a proxy and lack direct prediction of clinical instability or treatment needs. Here we present APRICOT-M, a state-space model to predict real-time ICU acuity outcomes and transitions, and the need for life-sustaining therapies within the next four hours. The model integrates vital signs, laboratory results, medications, assessment scores, and patient characteristics, to make predictions, handling sparse, irregular data efficiently. Our model is trained on over 140,000 ICU admissions across 55 hospitals and validated on external and real-time data, outperforming clinical scores in predicting mortality and instability. The model demonstrates clinical relevance, with physicians reporting alerts as actionable and timely in a substantial portion of cases. These results highlight APRICOT-M's potential to support earlier, more informed ICU interventions.
Authors
- Jeremy A. Balch (ORCID: https://orcid.org/0000-0002-1826-7884)
- Tezcan Ozrazgat‐Baslanti (ORCID: https://orcid.org/0000-0002-1158-9928)
- Parisa Rashidi (ORCID: https://orcid.org/0000-0003-4530-2048)
- Ziyuan Guan (ORCID: https://orcid.org/0009-0009-4824-6927)
- Azra Bihorac (ORCID: https://orcid.org/0000-0002-5745-2863)
- Benjamin Shickel (ORCID: https://orcid.org/0000-0002-5304-7027)
- Brandon Silva (ORCID: https://orcid.org/0000-0002-3645-1562)
- Gloria Lipori (ORCID: https://orcid.org/0000-0001-5616-2701)
- Tyler John Loftus (ORCID: https://orcid.org/0000-0001-5354-443X)
- Andréa Davidson (ORCID: https://orcid.org/0000-0003-3234-2649)
- Kia Khezeli (ORCID: https://orcid.org/0000-0002-1982-9391)
- Yuanfang Ren (ORCID: https://orcid.org/0000-0002-4716-2408)
- Subhash Nerella (ORCID: https://orcid.org/0000-0003-2940-6517)
- Jiaqing Zhang (ORCID: https://orcid.org/0000-0002-6859-1260)
- Sabyasachi Bandyopadhyay (ORCID: https://orcid.org/0000-0003-4617-7832)
- Jessica Sena (ORCID: https://orcid.org/0000-0002-5128-3632)
- Miguel Á. Contreras
Institutions
- University of Florida (US)
- Stanford University (US)
Publication Details
- Journal
- Nature Communications
- Published
- 2025-08-08
- DOI
- https://doi.org/10.1038/s41467-025-62121-1
- Citations
- 1
- Primary Topic
- Healthcare Technology and Patient Monitoring
- Type
- article
- Field-Weighted Citation Impact
- 2.01
Funders
- National Science Foundation
- National Institutes of Health
- National Institute of Neurological Disorders and Stroke
- National Institute of Biomedical Imaging and Bioengineering