Real-time prediction of intensive care unit patient acuity and therapy requirements using state-space modelling

Abstract 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 predi...

Full description

Saved in:
Bibliographic Details
Main Authors: Miguel Contreras, Brandon Silva, Benjamin Shickel, Andrea Davidson, Tezcan Ozrazgat-Baslanti, Yuanfang Ren, Ziyuan Guan, Jeremy Balch, Jiaqing Zhang, Sabyasachi Bandyopadhyay, Tyler Loftus, Kia Khezeli, Gloria Lipori, Jessica Sena, Subhash Nerella, Azra Bihorac, Parisa Rashidi
Format: Article
Language:English
Published: Nature Portfolio 2025-08-01
Series:Nature Communications
Online Access:https://doi.org/10.1038/s41467-025-62121-1
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849234657768374272
author Miguel Contreras
Brandon Silva
Benjamin Shickel
Andrea Davidson
Tezcan Ozrazgat-Baslanti
Yuanfang Ren
Ziyuan Guan
Jeremy Balch
Jiaqing Zhang
Sabyasachi Bandyopadhyay
Tyler Loftus
Kia Khezeli
Gloria Lipori
Jessica Sena
Subhash Nerella
Azra Bihorac
Parisa Rashidi
author_facet Miguel Contreras
Brandon Silva
Benjamin Shickel
Andrea Davidson
Tezcan Ozrazgat-Baslanti
Yuanfang Ren
Ziyuan Guan
Jeremy Balch
Jiaqing Zhang
Sabyasachi Bandyopadhyay
Tyler Loftus
Kia Khezeli
Gloria Lipori
Jessica Sena
Subhash Nerella
Azra Bihorac
Parisa Rashidi
author_sort Miguel Contreras
collection DOAJ
description Abstract 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.
format Article
id doaj-art-ea94d1a648244fc0bd8f5cde5e02ceab
institution Kabale University
issn 2041-1723
language English
publishDate 2025-08-01
publisher Nature Portfolio
record_format Article
series Nature Communications
spelling doaj-art-ea94d1a648244fc0bd8f5cde5e02ceab2025-08-20T04:03:03ZengNature PortfolioNature Communications2041-17232025-08-0116111510.1038/s41467-025-62121-1Real-time prediction of intensive care unit patient acuity and therapy requirements using state-space modellingMiguel Contreras0Brandon Silva1Benjamin Shickel2Andrea Davidson3Tezcan Ozrazgat-Baslanti4Yuanfang Ren5Ziyuan Guan6Jeremy Balch7Jiaqing Zhang8Sabyasachi Bandyopadhyay9Tyler Loftus10Kia Khezeli11Gloria Lipori12Jessica Sena13Subhash Nerella14Azra Bihorac15Parisa Rashidi16Department of Biomedical Engineering, University of FloridaIntelligent Clinical Care Center (IC3), University of FloridaIntelligent Clinical Care Center (IC3), University of FloridaIntelligent Clinical Care Center (IC3), University of FloridaIntelligent Clinical Care Center (IC3), University of FloridaIntelligent Clinical Care Center (IC3), University of FloridaIntelligent Clinical Care Center (IC3), University of FloridaIntelligent Clinical Care Center (IC3), University of FloridaIntelligent Clinical Care Center (IC3), University of FloridaDepartment of Medicine, Stanford UniversityIntelligent Clinical Care Center (IC3), University of FloridaDepartment of Biomedical Engineering, University of FloridaDeparment of Pharmaceutical Outcomes & Policy, University of FloridaDepartment of Biomedical Engineering, University of FloridaDepartment of Biomedical Engineering, University of FloridaIntelligent Clinical Care Center (IC3), University of FloridaDepartment of Biomedical Engineering, University of FloridaAbstract 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.https://doi.org/10.1038/s41467-025-62121-1
spellingShingle Miguel Contreras
Brandon Silva
Benjamin Shickel
Andrea Davidson
Tezcan Ozrazgat-Baslanti
Yuanfang Ren
Ziyuan Guan
Jeremy Balch
Jiaqing Zhang
Sabyasachi Bandyopadhyay
Tyler Loftus
Kia Khezeli
Gloria Lipori
Jessica Sena
Subhash Nerella
Azra Bihorac
Parisa Rashidi
Real-time prediction of intensive care unit patient acuity and therapy requirements using state-space modelling
Nature Communications
title Real-time prediction of intensive care unit patient acuity and therapy requirements using state-space modelling
title_full Real-time prediction of intensive care unit patient acuity and therapy requirements using state-space modelling
title_fullStr Real-time prediction of intensive care unit patient acuity and therapy requirements using state-space modelling
title_full_unstemmed Real-time prediction of intensive care unit patient acuity and therapy requirements using state-space modelling
title_short Real-time prediction of intensive care unit patient acuity and therapy requirements using state-space modelling
title_sort real time prediction of intensive care unit patient acuity and therapy requirements using state space modelling
url https://doi.org/10.1038/s41467-025-62121-1
work_keys_str_mv AT miguelcontreras realtimepredictionofintensivecareunitpatientacuityandtherapyrequirementsusingstatespacemodelling
AT brandonsilva realtimepredictionofintensivecareunitpatientacuityandtherapyrequirementsusingstatespacemodelling
AT benjaminshickel realtimepredictionofintensivecareunitpatientacuityandtherapyrequirementsusingstatespacemodelling
AT andreadavidson realtimepredictionofintensivecareunitpatientacuityandtherapyrequirementsusingstatespacemodelling
AT tezcanozrazgatbaslanti realtimepredictionofintensivecareunitpatientacuityandtherapyrequirementsusingstatespacemodelling
AT yuanfangren realtimepredictionofintensivecareunitpatientacuityandtherapyrequirementsusingstatespacemodelling
AT ziyuanguan realtimepredictionofintensivecareunitpatientacuityandtherapyrequirementsusingstatespacemodelling
AT jeremybalch realtimepredictionofintensivecareunitpatientacuityandtherapyrequirementsusingstatespacemodelling
AT jiaqingzhang realtimepredictionofintensivecareunitpatientacuityandtherapyrequirementsusingstatespacemodelling
AT sabyasachibandyopadhyay realtimepredictionofintensivecareunitpatientacuityandtherapyrequirementsusingstatespacemodelling
AT tylerloftus realtimepredictionofintensivecareunitpatientacuityandtherapyrequirementsusingstatespacemodelling
AT kiakhezeli realtimepredictionofintensivecareunitpatientacuityandtherapyrequirementsusingstatespacemodelling
AT glorialipori realtimepredictionofintensivecareunitpatientacuityandtherapyrequirementsusingstatespacemodelling
AT jessicasena realtimepredictionofintensivecareunitpatientacuityandtherapyrequirementsusingstatespacemodelling
AT subhashnerella realtimepredictionofintensivecareunitpatientacuityandtherapyrequirementsusingstatespacemodelling
AT azrabihorac realtimepredictionofintensivecareunitpatientacuityandtherapyrequirementsusingstatespacemodelling
AT parisarashidi realtimepredictionofintensivecareunitpatientacuityandtherapyrequirementsusingstatespacemodelling