EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Accelerating Wound Healing Through Deep Reinforcement Learning: A Data-Driven Approach to Optimal Treatment

Fan Lu, Ksenia Zlobina, Prabhat Baniya iD, Houpu Li iD, Nicholas Rondoni iD, Narges Asefifeyzabadi, Wan Shen Hee iD, Maryam Tebyani, Kaelan Schorger, Celeste Franco iD, Michelle Bagood, Mircea Teodorescu und 3 weitere

Bioengineering · 11.07.2025 · 12 (7) · 756

DOI: 10.3390/bioengineering12070756 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioengineering, online erschienen am 11.07.2025. Verfasst von Fan Lu und 14 weiteren Autor:innen. Beteiligte Einrichtung: Applied Mathematics, Baskin Engineering, University of California Santa Cruz, Santa Cruz, CA 95060, USA. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: DARPA, Office of Naval Research, Defense Advanced Research Projects Agency (DARPA).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Advancements in bioelectronic sensors and actuators have paved the way for real-time monitoring and control of the progression of wound healing. Real-time monitoring allows for precise adjustment of treatment strategies to align them with an individual’s unique biological response. However, due to the complexities of human–drug interactions and a lack of predictive models, it is challenging to determine how one should adjust drug dosage to achieve the desired biological response. This work proposes an adaptive closed-loop control framework that integrates deep learning, optimal control, and reinforcement learning to update treatment strategies in real time, with the goal of accelerating wound closure. The proposed approach eliminates the need for mathematical modeling of complex nonlinear wound-healing dynamics. We demonstrate the convergence of the controller via an in silico experimental setup, where the proposed approach successfully accelerated the wound-healing process by 17.71%. Finally, we share the experimental setup and results of an in vivo implementation to highlight the translational potential of our work. Our data-driven model suggests that the treatment strategy, as determined by our deep reinforcement learning algorithm, results in an accelerated onset of inflammation and subsequent transition to proliferation in a porcine wound model.

Schlagwörter

Stichwörter der Autor:innen

biomedical engineeringdeep reinforcement learningwound healing

Autor:innen und Institutionen

  • Applied Mathematics, Baskin Engineering, University of California Santa Cruz, Santa Cruz, CA 95060, USA.
  • Electrical and Computer Engineering, Baskin Engineering, University of California Santa Cruz, Santa Cruz, CA 95060, USA.
  • Biomedical Engineering, University of Southern California, Los Angeles, CA 90089, USA.
  • Bioengineering Department, Clemson University, Clemson, SC 29634, USA.
  • Department of Dermatology, University of California Davis, Davis, CA 95616, USA.

ORCID-Profile: Prabhat Baniya, Houpu Li, Nicholas Rondoni, Wan Shen Hee, Celeste Franco, Rivkah Isseroff, Marcella Gomez

Förderung

  • DARPA
  • Office of Naval Research
  • Defense Advanced Research Projects Agency (DARPA)

Zitieren

APA

Lu, F., Zlobina, K., Baniya, P., Li, H., Rondoni, N., Asefifeyzabadi, N., Hee, W. S., Tebyani, M., Schorger, K., Franco, C., Bagood, M., Teodorescu, M., Rolandi, M., Isseroff, R., & Gomez, M. (2025). Accelerating Wound Healing Through Deep Reinforcement Learning: A Data-Driven Approach to Optimal Treatment. Bioengineering, 12(7), 756. https://doi.org/10.3390/bioengineering12070756

Vancouver

Lu F, Zlobina K, Baniya P, Li H, Rondoni N, Asefifeyzabadi N, et al. Accelerating Wound Healing Through Deep Reinforcement Learning: A Data-Driven Approach to Optimal Treatment. Bioengineering. 2025;12(7):756. doi:10.3390/bioengineering12070756

BibTeX
@article{Lu2025,
  author = {Lu, Fan and Zlobina, Ksenia and Baniya, Prabhat and Li, Houpu and Rondoni, Nicholas and Asefifeyzabadi, Narges and Hee, Wan Shen and Tebyani, Maryam and Schorger, Kaelan and Franco, Celeste and Bagood, Michelle and Teodorescu, Mircea and Rolandi, Marco and Isseroff, Rivkah and Gomez, Marcella},
  title = {Accelerating Wound Healing Through Deep Reinforcement Learning: A Data-Driven Approach to Optimal Treatment},
  journal = {Bioengineering},
  year = {2025},
  volume = {12},
  number = {7},
  pages = {756},
  doi = {10.3390/bioengineering12070756}
}
Kostenlos starten →