EUVIMEDEUVIMED entdecken
Open Access

Double deep Q-network-based multi-drug chemotherapy scheduling optimization

Behnoush Alizade, Ahmad Hajipour iD

Biomedical Engineering Letters · 2026-11 · 16 (6) · 1421-1437

DOI: 10.1007/s13534-026-00599-4 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biomedical Engineering Letters, online erschienen am 10.07.2026. Verfasst von Behnoush Alizade und 1 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Electrical & Computer Engineering, Hakim Sabzevari University, Sabzevar, 9617976487 Iran. Die Arbeit nennt 29 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Designing optimal chemotherapy schedules remains a fundamental challenge in oncology, requiring a careful balance between effective tumor suppression and the prevention of excessive systemic toxicity. In this study, a deep reinforcement learning-based control framework is proposed for optimizing multi-drug chemotherapy dosing strategies under physiological uncertainty and clinical safety constraints. Specifically, a Double Deep Q-Network (DDQN) algorithm is employed to learn adaptive dosing policies for a three-drug chemotherapy regimen within a dynamic tumor-toxicity modeling environment. The proposed framework optimizes the scheduling of three chemotherapeutic agents represented within a mechanistic PK/PD model using a DDQN approach. A multi-objective reward function is formulated to simultaneously promote tumor reduction while penalizing excessive toxicity and violations of dose constraints. Through simulations over 5000 training episodes and robustness analyses under parameter perturbations up to [Formula: see text], the DDQN-based controller demonstrates the ability to reduce the tumor population from [Formula: see text] cells to approximately 42 residual cells while maintaining aggregate toxicity below the imposed safety limit of 300 units, with a mean value of 274. Robustness analyses are conducted under significant physiological parameter variations (up to [Formula: see text]) and abrupt tumor growth disturbances, where the proposed approach consistently maintains bounded state trajectories and avoids constraint violations. These simulation-based results suggest that Double Deep Q-Network reinforcement learning may provide a useful framework for adaptive chemotherapy scheduling under uncertainty. However, further validation using experimentally derived datasets, retrospective clinical cohorts, and prospective studies is required before clinical applicability can be established.

Schlagwörter

Stichwörter der Autor:innen

Cancer chemotherapy optimizationDDQNDeep learningMulti-drug schedulingReinforcement learning

Autor:innen und Institutionen

  • Faculty of Electrical & Computer Engineering, Hakim Sabzevari University, Sabzevar, 9617976487 Iran.

ORCID-Profile: Ahmad Hajipour

Zitieren

APA

Alizade, B., & Hajipour, A. (2026). Double deep Q-network-based multi-drug chemotherapy scheduling optimization. Biomedical Engineering Letters, 16(6), 1421-1437. https://doi.org/10.1007/s13534-026-00599-4

Vancouver

Alizade B, Hajipour A. Double deep Q-network-based multi-drug chemotherapy scheduling optimization. Biomedical Engineering Letters. 2026;16(6):1421-1437. doi:10.1007/s13534-026-00599-4

BibTeX
@article{Alizade2026,
  author = {Alizade, Behnoush and Hajipour, Ahmad},
  title = {Double deep Q-network-based multi-drug chemotherapy scheduling optimization},
  journal = {Biomedical Engineering Letters},
  year = {2026},
  volume = {16},
  number = {6},
  pages = {1421--1437},
  doi = {10.1007/s13534-026-00599-4}
}
Kostenlos starten →