EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Nephrocast‐V: A Deep Learning Model for the Prediction of Vancomycin Trough Concentration Using Electronic Health Record Data

Ghodsieh Ghanbari iD, Craig Stevens iD, Eliah Aronoff-Spencer iD, Atul Malhotra iD, Shamim Nemati iD, Zaid Yousif iD

Pharmacotherapy: The Journal of Human Pharmacology and Drug Therapy · 2026-01 · 46 (1)

DOI: 10.1002/phar.70062 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Pharmacotherapy: The Journal of Human Pharmacology and Drug Therapy, online erschienen am 30.09.2025. Verfasst von Ghodsieh Ghanbari und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Informatics, University of California San Diego (UCSD) School of Medicine, La Jolla, California, USA. Hauptthemen laut MEDLINE: Vancomycin, Electronic Health Records, Anti-Bacterial Agents, Deep Learning. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: NHLBI NIH HHS, NIGMS NIH HHS, NLM NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Vancomycin is a critical antibiotic for treating methicillin‐resistant Staphylococcus aureus and other gram‐positive bacterial infections, but achieving and maintaining therapeutic trough concentrations is challenging.

Objectives

We hypothesized that a deep learning model could accurately predict vancomycin trough concentrations 2 days in advance in critically ill patients and provide recommendations for optimal dosing adjustments to achieve target drug concentrations.

Methods

We trained and validated the model using electronic health record (EHR) data from adults admitted to the University of California San Diego Health system intensive care units (ICUs) from January 1, 2016, to June 30, 2024. Features included patient demographics, comorbidities, vital signs, laboratory measurements, medications, and vancomycin dosing information. The model architecture combined Long Short‐Term Memory and Multi‐Head Attention layers, supplemented with skip connections to incorporate past dosage information at the final layer of the deep learning model. Model performance was evaluated using mean absolute error (MAE) and root mean square error (RMSE) metrics.

Results

A total of 2205 encounters met the eligibility criteria. The median age was 57 years, and the median ICU length of stay was 4.9 days. The model achieved an MAE of 3.15 mg/L and an RMSE of 4.17 mg/L, comparable to that of a critical care pharmacist aided by a Bayesian dosing software. Additionally, deviations from patient‐specific model‐based dose recommendations were generally associated with nontherapeutic vancomycin levels.

Conclusion

This study demonstrates the potential to leverage deep learning to individualize and support vancomycin therapeutic drug monitoring in critically ill patients.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

VancomycinElectronic Health RecordsAnti-Bacterial AgentsDeep LearningHumansMiddle AgedMaleFemaleAgedIntensive Care UnitsAdultCritical IllnessDrug MonitoringRetrospective Studies

Stichwörter der Autor:innen

acute kidney injurycritical caredeep learningmachine learningpharmacokineticsvancomycin

Substanzen

VancomycinAnti-Bacterial Agents

Autor:innen und Institutionen

  • Department of Biomedical Informatics, University of California San Diego (UCSD) School of Medicine, La Jolla, California, USA.
  • Department of Pharmacy, UC San Diego Health, San Diego, California, USA.
  • Design Lab, University of California San Diego, La Jolla, California, USA.
  • Division of Infectious Diseases and Global Public Health, Department of Medicine, UC San Diego School of Medicine, La Jolla, California, USA.
  • Division of Pulmonary, Critical Care, and Sleep Medicine, UCSD Department of Medicine, La Jolla, California, USA.
  • Skaggs School of Pharmacy and Pharmaceutical Sciences, UCSD, La Jolla, California, USA.

ORCID-Profile: Ghodsieh Ghanbari, Craig Stevens, Eliah Aronoff-Spencer, Atul Malhotra, Shamim Nemati, Zaid Yousif

Förderung

  • NHLBI NIH HHS
  • NIGMS NIH HHS
  • NLM NIH HHS
  • NIA NIH HHS
  • U.S. National Library of Medicine
  • National Institute of General Medical Sciences

Zitieren

APA

Ghanbari, G., Stevens, C., Aronoff-Spencer, E., Malhotra, A., Nemati, S., & Yousif, Z. (2026). Nephrocast‐V: A Deep Learning Model for the Prediction of Vancomycin Trough Concentration Using Electronic Health Record Data. Pharmacotherapy: The Journal of Human Pharmacology and Drug Therapy, 46(1). https://doi.org/10.1002/phar.70062

Vancouver

Ghanbari G, Stevens C, Aronoff-Spencer E, Malhotra A, Nemati S, Yousif Z. Nephrocast‐V: A Deep Learning Model for the Prediction of Vancomycin Trough Concentration Using Electronic Health Record Data. Pharmacotherapy: The Journal of Human Pharmacology and Drug Therapy. 2026;46(1). doi:10.1002/phar.70062

BibTeX
@article{Ghanbari2026,
  author = {Ghanbari, Ghodsieh and Stevens, Craig and Aronoff-Spencer, Eliah and Malhotra, Atul and Nemati, Shamim and Yousif, Zaid},
  title = {Nephrocast‐V: A Deep Learning Model for the Prediction of Vancomycin Trough Concentration Using Electronic Health Record Data},
  journal = {Pharmacotherapy: The Journal of Human Pharmacology and Drug Therapy},
  year = {2026},
  volume = {46},
  number = {1},
  doi = {10.1002/phar.70062}
}
Kostenlos starten →