EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Development of a Reinforcement Learning Algorithm to Optimize Corticosteroid Therapy in Critically Ill Patients with Sepsis

Razvan Bologheanu, Lorenz Kapral iD, Daniel Laxar iD, Mathias Maleczek iD, Christoph Dibiasi iD, Sebastian Zeiner iD, Asan Agibetov, Ari Ercole iD, Patrick Thoral iD, Paul Elbers, Clemens Heitzinger, Oliver Kimberger iD

Journal of Clinical Medicine · 14.02.2023 · 12 (4) · 1513

DOI: 10.3390/jcm12041513 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Clinical Medicine, online erschienen am 14.02.2023. Verfasst von Razvan Bologheanu und 11 weiteren Autor:innen. Beteiligte Einrichtung: Department of Anaesthesia, Intensive Care Medicine and Pain Medicine, Medical University of Vienna, 1090 Vienna, Austria. Die Arbeit wurde bisher 28-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

The optimal indication, dose, and timing of corticosteroids in sepsis is controversial. Here, we used reinforcement learning to derive the optimal steroid policy in septic patients based on data on 3051 ICU admissions from the AmsterdamUMCdb intensive care database.

Methods

We identified septic patients according to the 2016 consensus definition. An actor-critic RL algorithm using ICU mortality as a reward signal was developed to determine the optimal treatment policy from time-series data on 277 clinical parameters. We performed off-policy evaluation and testing in independent subsets to assess the algorithm’s performance.

Results

Agreement between the RL agent’s policy and the actual documented treatment reached 59%. Our RL agent’s treatment policy was more restrictive compared to the actual clinician behavior: our algorithm suggested withholding corticosteroids in 62% of the patient states, versus 52% according to the physicians’ policy. The 95% lower bound of the expected reward was higher for the RL agent than clinicians’ historical decisions. ICU mortality after concordant action in the testing dataset was lower both when corticosteroids had been withheld and when corticosteroids had been prescribed by the virtual agent. The most relevant variables were vital parameters and laboratory values, such as blood pressure, heart rate, leucocyte count, and glycemia.

Conclusions

Individualized use of corticosteroids in sepsis may result in a mortality benefit, but optimal treatment policy may be more restrictive than the routine clinical practice. Whilst external validation is needed, our study motivates a ‘precision-medicine’ approach to future prospective controlled trials and practice.

Schlagwörter

Stichwörter der Autor:innen

artificial intelligencecorticosteroidsoutcomesreinforcement learningsepsis

Autor:innen und Institutionen

  • Department of Anaesthesia, Intensive Care Medicine and Pain Medicine, Medical University of Vienna, 1090 Vienna, Austria.
  • Ludwig Boltzmann Institute for Digital Health and Patient Safety, 1090 Vienna, Austria.
  • Centre for Artificial Intelligence in Medicine, University of Cambridge, Cambridge CB2 0QQ, UK.
  • Department of Intensive Care Medicine, Laboratory for Critical Care Computational Intelligence, Amsterdam UMC, Vrije Universiteit, 1081 HV Amsterdam, The Netherlands.
  • Institute of Analysis and Scientific Computing, Department of Mathematics and Geoinformation, Technical University of Vienna, 1040 Vienna, Austria.

ORCID-Profile: Lorenz Kapral, Daniel Laxar, Mathias Maleczek, Christoph Dibiasi, Sebastian Zeiner, Ari Ercole, Patrick Thoral, Oliver Kimberger

Zitieren

APA

Bologheanu, R., Kapral, L., Laxar, D., Maleczek, M., Dibiasi, C., Zeiner, S., Agibetov, A., Ercole, A., Thoral, P., Elbers, P., Heitzinger, C., & Kimberger, O. (2023). Development of a Reinforcement Learning Algorithm to Optimize Corticosteroid Therapy in Critically Ill Patients with Sepsis. Journal of Clinical Medicine, 12(4), 1513. https://doi.org/10.3390/jcm12041513

Vancouver

Bologheanu R, Kapral L, Laxar D, Maleczek M, Dibiasi C, Zeiner S, et al. Development of a Reinforcement Learning Algorithm to Optimize Corticosteroid Therapy in Critically Ill Patients with Sepsis. Journal of Clinical Medicine. 2023;12(4):1513. doi:10.3390/jcm12041513

BibTeX
@article{Bologheanu2023,
  author = {Bologheanu, Razvan and Kapral, Lorenz and Laxar, Daniel and Maleczek, Mathias and Dibiasi, Christoph and Zeiner, Sebastian and Agibetov, Asan and Ercole, Ari and Thoral, Patrick and Elbers, Paul and Heitzinger, Clemens and Kimberger, Oliver},
  title = {Development of a Reinforcement Learning Algorithm to Optimize Corticosteroid Therapy in Critically Ill Patients with Sepsis},
  journal = {Journal of Clinical Medicine},
  year = {2023},
  volume = {12},
  number = {4},
  pages = {1513},
  doi = {10.3390/jcm12041513}
}
Kostenlos starten →