Skip to content
DraconiticResearch
Search Sources API
197,768 studies31 sourcesUpdated 14 min ago
Peer-reviewedCC BYFrontiers in pharmacology

Exploratory machine-learning analysis of bevacizumab exposure and circulating VEGF dynamics in patients with cancer

  • Ileana Theofili1
  • Elias Liolis2
  • Angelos Koutras2
  • Vangelis D. Karalis1
  • Gregory Sivolapenko3
  1. 1Department of Pharmacy, National and Kapodistrian University of Athens , ,
  2. 2Department of Medicine, University of Patras , ,
  3. 3Department of Pharmacy, University of Patras , ,
Read full textPDFDOICite

Abstract

Introduction: This study explored pharmacokinetic and pharmacodynamic factors associated with circulating vascular endothelial growth factor (VEGF) dynamics during bevacizumab treatment.

Methods: A secondary analysis was conducted using data from 74 patients with breast, ovarian, cervical, non-small cell lung, or colorectal cancer. Paired pre- and post-infusion serum concentrations of bevacizumab and VEGF were measured by ELISA. Exploratory dimensionality-reduction methods and supervised tree-based models were applied. Artificial neural networks were used only as a complementary exploratory analysis on the same dataset.

Results: The main outcome of the analysis was VEGF_D, the absolute difference between the paired VEGF concentrations. The supervised models did not perform above the naive three-class benchmark; therefore, their variable-importance outputs were treated as secondary, model-specific, and hypothesis-generating observations. The results show exploratory model patterns of bevacizumab exposure and circulating VEGF dynamics. We did not assess clinical efficacy, safety results, and other dosing strategies in this study.

Discussion: The results do not support clinical implementation, personalized dosing, or treatment optimization and need to be confirmed in large independent cohorts.

Related

  1. Exposure to second-generation antipsychotics increases circulating small extracellular vesicles that promote insulin resistance in hepatocytes
    Vitor Ferreira, Rosa Alén, Dora Koller +10
    Journal of Physiology and BiochemistryPeer-reviewedCC BY 4.0Full textMolecular biology & gene regulationPMC
  2. An exploratory 12-week pilot study of gut microbiota and body-weight patterns during sodium nitrite exposure and Lactobacillus plantarum 299v supplementation in Wistar rats.
    Emre Duman, Alev Keser, Tuğçe Nur Balcı +4
    BMC microbiologyPeer-reviewedCC BY-NC-NDFull textMolecular biology & gene regulationEurope PMCDOAJ
  3. Blood Cell Intracellular pH Dynamics and Metabolic Biomarkers Under Simulated Postmortem Interval Conditions: An Exploratory Pilot In Vitro Study
    Paulino D. Ndunduma, Carolina Cordeiro, Susana Faria +3
    International Journal of Molecular SciencesPeer-reviewedCC BY 4.0General biochemistryCrossref
  4. The Trajectory Statistics of Biological Exploratory Dynamics
    S. D. Mahdavi, G. L. Salmon, M. Ashok +4
    bioRxivPreprintCC BYFull textBiophysicsbioRxiv
  5. Cross-Disease Transcriptomic Signatures Shared by NAFLD and MI: Multicohort Machine-Learning Analysis and Exploratory IDI1 Expression Assessment
    Jilei Qiao, Shuran Chen, Shuo Li +4
    International Journal of Molecular SciencesPeer-reviewedCC BY 4.0Full textMolecular biology & gene regulationCrossrefEurope PMC

Cite

BibTeXRIS
BibTeX
@article{theofili2026exploratory,
  title = {{Exploratory machine-learning analysis of bevacizumab exposure and circulating VEGF dynamics in patients with cancer}},
  author = {Ileana Theofili and Elias Liolis and Angelos Koutras and Vangelis D. Karalis and Gregory Sivolapenko},
  journal = {Frontiers in pharmacology},
  year = {2026},
  month = oct,
  doi = {10.3389/fphar.2026.1899527},
  url = {https://europepmc.org/article/PMC/PMC13690702},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - Exploratory machine-learning analysis of bevacizumab exposure and circulating VEGF dynamics in patients with cancer
AU  - Ileana Theofili
AU  - Elias Liolis
AU  - Angelos Koutras
AU  - Vangelis D. Karalis
AU  - Gregory Sivolapenko
PY  - 2026
DA  - 2026/10/09
JO  - Frontiers in pharmacology
DO  - 10.3389/fphar.2026.1899527
UR  - https://europepmc.org/article/PMC/PMC13690702
AB  - Introduction: This study explored pharmacokinetic and pharmacodynamic factors associated with circulating vascular endothelial growth factor (VEGF) dynamics during bevacizumab treatment.  Methods: A secondary analysis was conducted using data from 74 patients with breast, ovarian, cervical, non-small cell lung, or colorectal cancer. Paired pre- and post-infusion serum concentrations of bevacizumab and VEGF were measured by ELISA. Exploratory dimensionality-reduction methods and supervised tree-based models were applied. Artificial neural networks were used only as a complementary exploratory analysis on the same dataset.  Results: The main outcome of the analysis was VEGF_D, the absolute difference between the paired VEGF concentrations. The supervised models did not perform above the naive three-class benchmark; therefore, their variable-importance outputs were treated as secondary, model-specific, and hypothesis-generating observations. The results show exploratory model patterns of bevacizumab exposure and circulating VEGF dynamics. We did not assess clinical efficacy, safety results, and other dosing strategies in this study.  Discussion: The results do not support clinical implementation, personalized dosing, or treatment optimization and need to be confirmed in large independent cohorts.
SN  - 1663-9812
ER  -