EUVIMEDEUVIMED entdecken
Open Access

Toward digital twins in the intensive care unit: a medication management case study

Behnaz Eslami iD, Majid Afshar iD, Samie Tootooni iD, Timothy A Miller iD, Matthew M Churpek, Yanjun Gao iD, Dmitriy Dligach iD

Journal of the American Medical Informatics Association · 2025

DOI: 10.1093/jamia/ocaf127 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of the American Medical Informatics Association, 2025. Verfasst von Behnaz Eslami und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, Loyola University Chicago, Chicago, IL 60626, United States. Hauptthemen laut MEDLINE: Intensive Care Units, Electronic Health Records, Medication Therapy Management, Natural Language Processing. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIDA NIH HHS, NLM NIH HHS, NHLBI NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

To evaluate the efficacy of digital twins developed using a large language model (LLaMA-3), fine-tuned with Low-Rank Adapters (LoRA) on intensive care units (ICU) physician notes, and to determine whether specialty-specific training enhances treatment recommendation accuracy compared to other ICU specialties or zero-shot baselines. Materials and Methods Digital twins were created using LLaMA-3 fine-tuned on discharge summaries from the Medical Information Mart for Intensive Care III dataset, where medications were masked to construct training and testing datasets. The medical ICU dataset (1000 notes) was used for evaluation, and performance was assessed using Bidirectional Encoder Representations from Transformers Score (BERTScore) and ROUGE-L. A zero-shot baseline model, relying solely on contextual instructions without training, was also evaluated. While our approach moves toward digital twin capabilities, it does not incorporate real-time, patient-specific electronic health records data and can be viewed as an ICU specialty-level language model adaptation.

Results

Models fine-tuned on medical ICU notes achieved the highest BERTScore (0.842), outperforming models trained on other specialties or mixed datasets. Zero-shot models showed the lowest performance, highlighting the importance of training.

Discussion

The findings demonstrate that specialty-specific training significantly improves treatment recommendation accuracy in digital twins compared to generalized or zero-shot approaches. Tailoring models to specific ICU domains strengthens their clinical decision-support capabilities.

Conclusion

Context-specific fine-tuning of LLMs is crucial for developing effective digital twins, offering foundational insights for personalized clinical decision support.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Intensive Care UnitsElectronic Health RecordsMedication Therapy ManagementNatural Language ProcessingDecision Support Systems, ClinicalHumans

Stichwörter der Autor:innen

digital twinsintensive care unitlarge language models

Autor:innen und Institutionen

  • Department of Computer Science, Loyola University Chicago, Chicago, IL 60626, United States.
  • Department of Health Informatics and Data Science, Loyola University Chicago, Maywood, IL 60153, United States.
  • Department of Medicine, University of Wisconsin-Madison, Madison, WI 53726, United States.
  • Computational Health Informatics Program, Boston Children's Hospital, Boston, MA 02215, United States.
  • Department of Pediatrics, Harvard Medical School, Boston, MA 02215, United States.
  • University of Colorado-Anschutz, Aurora, CO 80045, United States.

ORCID-Profile: Behnaz Eslami, Majid Afshar, Samie Tootooni, Timothy A Miller, Yanjun Gao, Dmitriy Dligach

Förderung

  • NIDA NIH HHS
  • NLM NIH HHS
  • NHLBI NIH HHS
  • National Heart, Lung, and Blood Institute
  • National Library of Medicine

Zitieren

APA

Eslami, B., Afshar, M., Tootooni, S., Miller, T. A., Churpek, M. M., Gao, Y., & Dligach, D. (2025). Toward digital twins in the intensive care unit: a medication management case study. Journal of the American Medical Informatics Association. https://doi.org/10.1093/jamia/ocaf127

Vancouver

Eslami B, Afshar M, Tootooni S, Miller TA, Churpek MM, Gao Y, et al. Toward digital twins in the intensive care unit: a medication management case study. Journal of the American Medical Informatics Association. 2025. doi:10.1093/jamia/ocaf127

BibTeX
@article{Eslami2025,
  author = {Eslami, Behnaz and Afshar, Majid and Tootooni, Samie and Miller, Timothy A and Churpek, Matthew M and Gao, Yanjun and Dligach, Dmitriy},
  title = {Toward digital twins in the intensive care unit: a medication management case study},
  journal = {Journal of the American Medical Informatics Association},
  year = {2025},
  doi = {10.1093/jamia/ocaf127}
}
Kostenlos starten →