EUVIMEDEUVIMED entdecken
Open Access

Explaining alerts from a pediatric risk prediction model using clinical text

Samuel Nycklemoe, Sriharsha Devarapu, Yanjun Gao iD, Kyle Carey, Nicholas Kuehnel, Neil Munjal, Priti Jani, Matthew Churpek, Dmitriy Dligach iD, Majid Afshar, Anoop Mayampurath

Journal of the American Medical Informatics Association · 2025

DOI: 10.1093/jamia/ocaf121 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of the American Medical Informatics Association, 2025. Verfasst von Samuel Nycklemoe und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biostatistics & Medical Informatics, University of Wisconsin-Madison, Madison, WI 53726, United States. Hauptthemen laut MEDLINE: Algorithms, Clinical Deterioration, Electronic Health Records. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NHLBI NIH HHS, NLM NIH HHS, NHLBI.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

Risk prediction models are used in hospitals to identify pediatric patients at risk of clinical deterioration, enabling timely interventions and rescue. The objective of this study was to develop a new explainer algorithm that uses a patient’s clinical notes to generate text-based explanations for risk prediction alerts. Materials and Methods We conducted a retrospective study of 39 406 patient admissions to the American Family Children’s Hospital at the University of Wisconsin-Madison (2009-2020). The pediatric Calculated Assessment of Risk and Triage (pCART) validated risk prediction model was used to identify children at risk for deterioration. A transformer model was trained to use clinical notes from the 12-hour period preceding each pCART score to predict whether a patient was flagged as at risk. Then, label-aware attention highlighted text phrases most important to an at-risk alert. The study cohort was randomly split into derivation (60%) and validation (20%) data, and a separate test (20%) was used to evaluate the explainer’s performance.

Results

Our pCART Explainer algorithm performed well in discriminating at-risk pCART alert vs no alert (c-statistic 0.805). Sample explanations from pCART Explainer revealed clinically important phrases such as “rapid breathing,” “fall risk,” “distension,” and “grunting,” thereby demonstrating excellent face validity.

Discussion

The pCART Explainer could quickly orient clinicians to the patient’s condition by drawing attention to key phrases in notes, potentially enhancing situational awareness and guiding decision-making.

Conclusion

We developed pCART Explainer, a novel algorithm that highlights text within clinical notes to provide medically relevant context about deterioration alerts, thereby improving the explainability of the pCART model.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AlgorithmsClinical DeteriorationElectronic Health RecordsHumansRetrospective StudiesRisk AssessmentChildChild, PreschoolInfantTriageFemaleHospitals, PediatricMaleDecision Support Systems, ClinicalWisconsin

Stichwörter der Autor:innen

clinical noteselectronic health recordsexplainabilitypediatricsrisk predictions

Autor:innen und Institutionen

  • Department of Biostatistics & Medical Informatics, University of Wisconsin-Madison, Madison, WI 53726, United States.
  • Department of Biomedical Informatics, University of Colorado Anschutz Medical Campus, Aurora, CO 80045, United States.
  • Department of Medicine, University of Chicago, Chicago, IL 60637, United States.
  • Department of Emergency Medicine, University of Wisconsin-Madison, Madison, WI 53726, United States.
  • Department of Pediatrics, University of Wisconsin-Madison, Madison, WI 53726, United States.
  • Department of Pediatrics, University of Chicago, Chicago, IL 60637, United States.

ORCID-Profile: Yanjun Gao, Dmitriy Dligach

Förderung

  • NHLBI NIH HHS
  • NLM NIH HHS
  • NHLBI
  • NLM

Zitieren

APA

Nycklemoe, S., Devarapu, S., Gao, Y., Carey, K., Kuehnel, N., Munjal, N., Jani, P., Churpek, M., Dligach, D., Afshar, M., & Mayampurath, A. (2025). Explaining alerts from a pediatric risk prediction model using clinical text. Journal of the American Medical Informatics Association. https://doi.org/10.1093/jamia/ocaf121

Vancouver

Nycklemoe S, Devarapu S, Gao Y, Carey K, Kuehnel N, Munjal N, et al. Explaining alerts from a pediatric risk prediction model using clinical text. Journal of the American Medical Informatics Association. 2025. doi:10.1093/jamia/ocaf121

BibTeX
@article{Nycklemoe2025,
  author = {Nycklemoe, Samuel and Devarapu, Sriharsha and Gao, Yanjun and Carey, Kyle and Kuehnel, Nicholas and Munjal, Neil and Jani, Priti and Churpek, Matthew and Dligach, Dmitriy and Afshar, Majid and Mayampurath, Anoop},
  title = {Explaining alerts from a pediatric risk prediction model using clinical text},
  journal = {Journal of the American Medical Informatics Association},
  year = {2025},
  doi = {10.1093/jamia/ocaf121}
}
Kostenlos starten →