Detail

Keywords

Artificial Intelligence; Decision Support Systems, Clinical; Intensive Care; Intensive Care Units; Machine Learning

Research group(s)

• AGD
  Head: Oliver Kimberger
  Research Area: Perioperative Data Science
  Members:
  Mohammad Mahdi Azarbeik
  Stefan Bartos
  Christoph Dibiasi
  Henry Forman
  Fabian Peter Hammerle
  Lorenz Kapral
  Oliver Kimberger
  Daniel Laxar
  Maleczek Mathias
  Georgina Petropoulou
  Clemens Pramhas
  Sebastian Zeiner

Research interests

I work on machine learning with a focus on reinforcement learning, decision support in intensive care, and large language models.

My work applies RL-based methods to clinical data to help improve critical care outcomes, bridging the gap between algorithmic theory and real-world medical practice.

Techniques, methods & infrastructure

• Clinical AI & Decision Support

Reinforcement Learning for Critical Care, Clinical Decision Support Systems, Off-Policy Evaluation.

• Machine Learning

Deep Reinforcement Learning, Generative AI, LLMs, Self-Supervised Learning.

• Biomedical Data

Physiological Time Series, Multi-Modal Clinical Data (EHR, Structured, Imaging), ICU Databases.

• Robotics

State Estimation, Data Fusion, Localization.

Selected publications

1. Azarbeik, M. M. et al. (2026) “Learning and evaluating improved reinforcement learning-based policies for sepsis treatment on MIMIC-IV,” Journal of Critical Care. Edited by , 92, p. 155385. Available at: https://doi.org/10.1016/j.jcrc.2025.155385.
2. Kapral, L. et al. (2025) “Optimal timing for renal replacement therapy in critically ill patients using reinforcement learning algorithms,” Journal of Critical Care. Edited by , 86, p. 154964. Available at: https://doi.org/10.1016/j.jcrc.2024.154964.
3. Azarbeik, M.M. et al. (2023) “Augmenting inertial motion capture with SLAM using EKF and SRUKF data fusion algorithms,” Measurement. Edited by , 222, p. 113690. Available at: https://doi.org/10.1016/j.measurement.2023.113690.
4. Arzt, V. et al. (2024) “TU Wien at SemEval-2024 Task 6: Unifying Model-Agnostic and Model-Aware Techniques for Hallucination Detection,” Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024). Edited by , pp. 1183–1196. Available at: https://doi.org/10.18653/v1/2024.semeval-1.173.
5. Kapral, L. et al. (2025) “Optimized Renal Replacement Therapy Decisions in Intensive Care: A Reinforcement Learning Approach.” Edited by . Available at: https://doi.org/10.21203/rs.3.rs-6243566/v1.