{
  "abstract": "Intensive care unit (ICU) monitoring systems face a critical gap: translating continuous physiological data into interpretable patterns that support clinical assessment. Existing approaches rely on static thresholds or severity scores that fail to capture dynamic disease progression patterns and provide limited insight into why patients change over time. We developed STREAM (State Trajectory Representation and Evolution-Aware Monitoring), which models each patient as a point in a multidimensional physiological space and applies geometric analysis of routine ICU data to track physiological instability. STREAM analyzes 26 routinely collected clinical measurements using optimal transport theory to discover data-derived physiological states without predefined categories and maps each patient to their nearest state. We evaluated STREAM using the multicenter eICU Collaborative Research Database (N = 158,294) for development and MIMIC-IV (N = 84,517) for external validation. STREAM identified five reproducible data-derived physiological states with distinct clinical signatures. Patients who spent less than 10% of their ICU stay within their expected state (state outliers) had ICU mortality of 37.6%, 16-fold higher than those who remained within their assigned states (2.3%). Mortality prediction achieved an area under the receiver operating characteristic curve of 0.863 at 8 hours and 0.903 at 72 hours, with excellent calibration (expected calibration error of 0.002). External validation on MIMIC-IV maintained robust performance (0.798 and 0.857, respectively), with state outliers exhibiting 10-fold higher mortality (33.5% vs. 3.2%). Feature importance analysis identified which laboratory values and vital signs are associated with movement toward higher-risk states, providing interpretable clinical explanations. STREAM provides transparent monitoring across data-derived physiological states, linking state dynamics with outcome prediction. Strong discrimination, calibration, and reproducibility across multicenter datasets support the method’s potential for prospective evaluation. Author summary: We created STREAM, a monitoring system that tracks how critically ill patients move through different data-derived physiological states during their intensive care unit stay. Current monitoring approaches compress complex patient data into single scores that lose important information about how different organ systems interact and change over time. STREAM uses a mathematical approach called optimal transport to identify distinct patterns in routine blood tests and vital signs, then tracks each patient’s movement through these patterns. We found that patients whose measurements consistently fall outside their expected pattern, even when no single measurement is extreme, face dramatically higher mortality risk. In our largest dataset of over 158,000 patients, these outlier patients had 16 times higher mortality than those who remained within expected patterns. Importantly, STREAM explains which specific measurements are most associated with each patient’s trajectory, giving clinicians interpretable information rather than just a risk number. When tested on an independent dataset of over 84,000 patients from a different hospital, the system maintained strong performance without any retraining, suggesting it captures fundamental patterns of critical illness that generalize across institutions.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Radiology, University of Michigan, Ann Arbor, Michigan, United States of America",
    "Department of Radiology and Imaging Sciences, Wallace H. Coulter Department of Biomedical Engineering, School of Electrical and Computer Engineering, Emory University and Georgia Institute of Technology, Atlanta, Georgia, United States of America",
    "Division of Pulmonary and Critical Care Medicine, Department of Internal Medicine, University of Michigan, Ann Arbor, Michigan, United States of America"
  ],
  "article_type": "Research Article",
  "arxiv": null,
  "author_total": 6,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Ali Namvar"
    },
    {
      "affs": [
        1
      ],
      "name": "Sundaresh Ram"
    },
    {
      "affs": [
        2
      ],
      "name": "Wassim W. Labaki"
    },
    {
      "name": "Stefanie Galban"
    },
    {
      "name": "Njira L. Lugogo"
    },
    {
      "name": "Craig J. Galban"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/9ehepd5g3czxw.bib",
  "cited_by": 0,
  "doi": "10.1371/journal.pdig.0001753",
  "fulltext_url": "https://journals.plos.org/digitalhealth/article?id=10.1371/journal.pdig.0001753",
  "id": "9ehepd5g3czxw",
  "issns": [
    "2767-3170"
  ],
  "landing_url": "https://journals.plos.org/digitalhealth/article?id=10.1371/journal.pdig.0001753",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "1702|Machine Learning in Healthcare"
    ],
    [
      "plos",
      "/Biology and life sciences/Anatomy/Body fluids/Blood/Platelets"
    ],
    [
      "plos",
      "/Biology and life sciences/Biochemistry/Biomarkers/Creatinine"
    ],
    [
      "plos",
      "/Biology and life sciences/Biochemistry/Proteins/Hemoglobin"
    ],
    [
      "plos",
      "/Biology and life sciences/Cell biology/Cellular types/Animal cells/Blood cells/Platelets"
    ],
    [
      "plos",
      "/Biology and life sciences/Physiology/Body fluids/Blood/Platelets"
    ],
    [
      "plos",
      "/Biology and life sciences/Population biology/Population metrics/Death rates"
    ],
    [
      "plos",
      "/Medicine and health sciences/Anatomy/Body fluids/Blood/Platelets"
    ],
    [
      "plos",
      "/Medicine and health sciences/Epidemiology/Medical risk factors"
    ],
    [
      "plos",
      "/Medicine and health sciences/Health care/Health care facilities/Hospitals/Intensive care units"
    ],
    [
      "plos",
      "/Physical sciences/Chemistry/Chemical compounds/Bicarbonates"
    ],
    [
      "plos",
      "/Physical sciences/Mathematics/Statistics/Statistical methods/Forecasting"
    ],
    [
      "plos",
      "/Research and analysis methods/Mathematical and statistical techniques/Statistical methods/Forecasting"
    ]
  ],
  "openalex": "W7215106669",
  "pdf_url": "https://journals.plos.org/digitalhealth/article/file?id=10.1371/journal.pdig.0001753&type=printable",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-01",
  "publisher": "Public Library of Science",
  "ris": "https://research.draconitic.com/paper/9ehepd5g3czxw.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:37Z",
      "native_id": "10.1371/journal.pdig.0001753",
      "source": "plos",
      "url": "https://journals.plos.org/digitalhealth/article?id=10.1371/journal.pdig.0001753"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "plos:statistical methods",
      "subfield": "statistics"
    },
    {
      "field": "medicine",
      "origin": "plos:anatomy",
      "subfield": "physiology"
    }
  ],
  "title": "STREAM: A data-driven framework for physiological state monitoring in ICU patients",
  "title_text": "STREAM: A data-driven framework for physiological state monitoring in ICU patients",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:17:37Z",
  "url": "https://research.draconitic.com/paper/9ehepd5g3czxw",
  "venue": "PLOS Digital Health",
  "versions": []
}