Skip to content
DraconiticResearch
Search Sources API
203,948 studies31 sourcesUpdated 35 min ago
Peer-reviewedCC BYJAMIA open

P-WIN deployment: real-time personalized machine learning to predict critical deterioration in a pediatric intensive care unit.

  • Eamonn Tweedy1
  • Sanjiv Mehta2,3,4
  • Sachin Grover1
  • Hannah R Stinson2,3
  • Victor M Ruiz1
  • Erika Pleskunas5
  • James Sannino6
  • Akira Nishisaki2,3
  • Fuchiang Rich Tsui1,2,3,7
7 affiliations
  1. 1Tsui Laboratory, Department of Biomedical and Health Informatics, Children's Hospital of Philadelphia, Philadelphia, PA 19146, United States.
  2. 2Division of Critical Care Medicine, Department of Anesthesiology and Critical Care Medicine, Children's Hospital of Philadelphia, Philadelphia, PA 19104, United States.
  3. 3Department of Anesthesiology and Critical Care, University of Pennsylvania, Philadelphia, PA 19104, United States.
  4. 4Department of Biomedical and Health Informatics, Children's Hospital of Philadelphia, Philadelphia, PA 19146, United States.
  5. 5Digital and Technology Services, Children's Hospital of Philadelphia, Philadelphia, PA 19104, United States.
  6. 6Center for Healthcare Quality and Analytics, Children's Hospital of Philadelphia, Philadelphia, PA 19104, United States.
  7. 7Department of Biostatistics, Epidemiology, and Informatics, University of Pennsylvania, Philadelphia, PA 19104, United States.
Read full textPDFDOICite

Abstract

Objectives

Early recognition of critical deterioration events (CDEs) in pediatric intensive care units (PICUs) is crucial to improving outcomes, but the real-time performance of machine-learning (ML)-based alert systems is rarely assessed. We prospectively evaluated the performance, operational utility, and deployment feasibility of the PICU Warning Index (P-WIN), a personalized ML alert system predicting CDE in the PICU.Materials and methods

In this prospective cohort study at a quaternary-care children's hospital, P-WIN estimated deterioration risk for PICU patients aged 0-24 years at 30-minute intervals between January 7 and April 7, 2026 using electronic health record data collected via Fast Healthcare Interoperability Resources and proprietary EPIC API endpoints. CDEs included cardiopulmonary resuscitation, initiation of extracorporeal membrane oxygenation, dilute (10 μg/mL) epinephrine bolus, or unplanned endotracheal intubation. P-WIN was compared to baseline workflows: an automated PICU Warning Tool and a clinician-huddle-based assessment. Primary measures were CDE-level sensitivity, admission-level positive predictive value (PPV), and alerts per patient-day.Results

Among 1005 PICU patients, 99 CDEs were experienced by 62 patients. P-WIN detected 73% of these CDE 1-24 hours in advance, outperforming the PICU Warning Tool (39%, P < .05) and huddle workflow (23%, P < .05). P-WIN generated 0.21 (95% CI, 0.18-0.23) alerts per patient-day. The PICU Warning Tool and huddle workflow had similar PPV to P-WIN.Conclusion

P-WIN detected significantly more CDEs than existing PICU Warning tool and huddle workflows while maintaining a similar PPV. Our findings underscore the feasibility of ML-based personalized warning systems to enhance shared situational awareness of PICU deterioration.

Related

  1. Unexplained neurological deterioration after acute brain injury: A structured intensive care framework for targeted continuous electroencephalogram.
    Kazunori Oda, Natsuki Nakatani, Tomo Kinoshita +1
    Surgical neurology internationalPeer-reviewedCC BY-NC-SAFull textNeurologyEurope PMCPMC
  2. Rapid whole-genome sequencing in the pediatric intensive care unit: from etiologic diagnosis to precision management—a narrative review
    Xin Yang, Di Liu
    Translational pediatricsPeer-reviewedCC BY-NC-NDFull textGeneral medicineEurope PMC
  3. Development and validation of a risk score to predict mortality in the pediatric intensive care unit using routinely collected data in Northwest Ethiopia: a retrospective study
    Yitayih Baylie Alamirew, Tamene Habitu Enyew, Mulualem Endeshaw Zeleke +3
    Scientific ReportsPeer-reviewedCC BY-NC-ND 4.0Crossref
  4. Reply-Letter to the editor. Nutritional Goals in Mechanically Ventilated Children: Impact of a Standardized Enteral Protocol in a Tertiary Pediatric Intensive Care Unit
    Arthur Gaudaire, Cyril Ceci, Héléna Huguet +7
    Clinical Nutrition ESPENPeer-reviewedCC BY 4.0Full textGeneral biologyEpidemiology & public healthHAL
  5. The evolution of sepsis care: from protocol-driven management to personalized intensive care
    Tim Rahmel, Benedikt H. Siegler, Markus A. Weigand +5
    InfectionPeer-reviewedCC BY 4.0Full text3 citedEpidemiology & public healthPMC

Cite

BibTeXRIS
BibTeX
@article{tweedy2026pwin,
  title = {{P-WIN deployment: real-time personalized machine learning to predict critical deterioration in a pediatric intensive care unit.}},
  author = {Eamonn Tweedy and Sanjiv Mehta and Sachin Grover and Hannah R Stinson and Victor M Ruiz and Erika Pleskunas and James Sannino and Akira Nishisaki and Fuchiang Rich Tsui},
  journal = {JAMIA open},
  year = {2026},
  month = oct,
  doi = {10.1093/jamiaopen/ooag202},
  url = {https://europepmc.org/article/MED/42899309},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - P-WIN deployment: real-time personalized machine learning to predict critical deterioration in a pediatric intensive care unit.
AU  - Eamonn Tweedy
AU  - Sanjiv Mehta
AU  - Sachin Grover
AU  - Hannah R Stinson
AU  - Victor M Ruiz
AU  - Erika Pleskunas
AU  - James Sannino
AU  - Akira Nishisaki
AU  - Fuchiang Rich Tsui
PY  - 2026
DA  - 2026/10/19
JO  - JAMIA open
DO  - 10.1093/jamiaopen/ooag202
UR  - https://europepmc.org/article/MED/42899309
AB  - Objectives  Early recognition of critical deterioration events (CDEs) in pediatric intensive care units (PICUs) is crucial to improving outcomes, but the real-time performance of machine-learning (ML)-based alert systems is rarely assessed. We prospectively evaluated the performance, operational utility, and deployment feasibility of the PICU Warning Index (P-WIN), a personalized ML alert system predicting CDE in the PICU.Materials and methods  In this prospective cohort study at a quaternary-care children's hospital, P-WIN estimated deterioration risk for PICU patients aged 0-24 years at 30-minute intervals between January 7 and April 7, 2026 using electronic health record data collected via Fast Healthcare Interoperability Resources and proprietary EPIC API endpoints. CDEs included cardiopulmonary resuscitation, initiation of extracorporeal membrane oxygenation, dilute (10 μg/mL) epinephrine bolus, or unplanned endotracheal intubation. P-WIN was compared to baseline workflows: an automated PICU Warning Tool and a clinician-huddle-based assessment. Primary measures were CDE-level sensitivity, admission-level positive predictive value (PPV), and alerts per patient-day.Results  Among 1005 PICU patients, 99 CDEs were experienced by 62 patients. P-WIN detected 73% of these CDE 1-24 hours in advance, outperforming the PICU Warning Tool (39%, P < .05) and huddle workflow (23%, P < .05). P-WIN generated 0.21 (95% CI, 0.18-0.23) alerts per patient-day. The PICU Warning Tool and huddle workflow had similar PPV to P-WIN.Conclusion  P-WIN detected significantly more CDEs than existing PICU Warning tool and huddle workflows while maintaining a similar PPV. Our findings underscore the feasibility of ML-based personalized warning systems to enhance shared situational awareness of PICU deterioration.
SN  - 2574-2531
ER  -