EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Predicting prolonged dalbavancin exposure using machine learning: a validated strategy for individualized redosing

Hamza Sayadi, Matthieu Gregoire, Yeleen Fromage, Mohamed Ksentini, Marc Labriffe, Caroline Monchaud, Cyrielle Codde, Jean-François Faucher, David Boutoille, Pierre Marquet, Jean-Baptiste Woillard iD

Antimicrobial Agents and Chemotherapy · 2026

DOI: 10.1128/aac.01363-25 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Antimicrobial Agents and Chemotherapy, 2026. Verfasst von Hamza Sayadi und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Pharmacology, Toxicology and Pharmacovigilance, Dupuytren University Hospital (CHU Dupuytren), Limoges, France. Hauptthemen laut MEDLINE: Teicoplanin, Anti-Bacterial Agents, Machine Learning. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Agence Nationale de la Recherche.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Dalbavancin is a long-acting lipoglycopeptide increasingly used off-label for complex Gram-positive infections requiring prolonged therapy. Its extended half-life enables simplified regimens, but interindividual pharmacokinetic variability and pathogen MIC heterogeneity complicate dosing. We developed and externally validated machine learning (ML) models to predict whether dalbavancin plasma concentrations remain above predefined pharmacokinetic/pharmacodynamic targets after two standard 1,500 mg doses (day 1/day 8 or day 1/day 15). Predictions were binary (adequate vs subtherapeutic concentration), directly reflecting the clinical decision to readminister a 1,500 mg dose. Models were trained on simulated PK profiles from a published population PK (popPK) model and evaluated in three independent settings: (i) simulated validation data sets from two alternative published popPK models, (ii) a real-world cohort from Limoges University Hospital ( n = 31), and (iii) a secondary cohort from Nantes University Hospital ( n = 7). Input features included age, body weight, creatinine clearance, MIC, and a single plasma concentration obtained before the second dose. Support vector machine models achieved high accuracy (>88%) and sensitivity (>90%) across testing sets and clinical validation cohorts. In clinical data sets, no false negatives were observed (limited by sample size), with overall accuracy approaching 95%. Compared with maximum a posteriori Bayesian estimation, ML achieved higher accuracy and sensitivity across validation cohorts, particularly by reducing false negatives. Predictions remained reliable through week 8, the clinically relevant exposure window. This ML-based approach enables early individualized redosing decisions using minimal clinical inputs. By complementing Bayesian forecasting and reducing reliance on serial sampling, it represents a pragmatic strategy to support model-informed precision dosing of dalbavancin.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

TeicoplaninAnti-Bacterial AgentsMachine LearningHumansMicrobial Sensitivity TestsMiddle AgedMaleFemaleSupport Vector MachineAgedAdultGram-Positive Bacterial InfectionsBayes Theorem

Stichwörter der Autor:innen

Monte Carlo simulationsdalbavancinemachine learningmodel-informed precision dosingpopulation pharmacokineticstherapeutic drug monitoring

Substanzen

TeicoplanindalbavancinAnti-Bacterial Agents

Autor:innen und Institutionen

  • Department of Pharmacology, Toxicology and Pharmacovigilance, Dupuytren University Hospital (CHU Dupuytren), Limoges, France.
  • Pharmacology & Transplantation INSERM U1248, University of Limoges, Limoges, France.
  • Clinical Pharmacology Department, Nantes University, Nantes University Hospital, Nantes, France.
  • Nantes University, Nantes University Hospital, Infection and Immunity: Targets and Drugs, IICiMed, UR 1155, Nantes, France.
  • Department of Infectious and Tropical Diseases, Dupuytren University Hospital (CHU Dupuytren), Limoges, France.
  • Infectious and Tropical Diseases Department, Nantes University, Nantes University Hospital, INSERM, CIC 1413, Nantes, France.

ORCID-Profile: Jean-Baptiste Woillard

Förderung

  • Agence Nationale de la Recherche

Zitieren

APA

Sayadi, H., Gregoire, M., Fromage, Y., Ksentini, M., Labriffe, M., Monchaud, C., Codde, C., Faucher, J. F., Boutoille, D., Marquet, P., & Woillard, J. B. (2026). Predicting prolonged dalbavancin exposure using machine learning: a validated strategy for individualized redosing. Antimicrobial Agents and Chemotherapy. https://doi.org/10.1128/aac.01363-25

Vancouver

Sayadi H, Gregoire M, Fromage Y, Ksentini M, Labriffe M, Monchaud C, et al. Predicting prolonged dalbavancin exposure using machine learning: a validated strategy for individualized redosing. Antimicrobial Agents and Chemotherapy. 2026. doi:10.1128/aac.01363-25

BibTeX
@article{Sayadi2026,
  author = {Sayadi, Hamza and Gregoire, Matthieu and Fromage, Yeleen and Ksentini, Mohamed and Labriffe, Marc and Monchaud, Caroline and Codde, Cyrielle and Faucher, Jean-François and Boutoille, David and Marquet, Pierre and Woillard, Jean-Baptiste},
  title = {Predicting prolonged dalbavancin exposure using machine learning: a validated strategy for individualized redosing},
  journal = {Antimicrobial Agents and Chemotherapy},
  year = {2026},
  doi = {10.1128/aac.01363-25}
}
Kostenlos starten →