Biography

Patrick leads the research group on AI for Clinical Decision-Making. His research focuses on building machine learning models that work reliably in real clinical environments — across different hospitals, patient populations, and over time. He is particularly interested in leveraging large-scale EHR data to develop foundation models that generalise beyond the settings they were trained on.

Since February 2026, he is the PI of GPT-MEDIC, a €1.5M ERC Starting Grant to develop and validate multicentre foundation models for ICU time-series data. He also coordinates MUI’s participation in INDICATE, a consortium building federated data infrastructure for intensive care across Europe.

Before joining Innsbruck, Patrick was a Humboldt Research Fellow at Charité – Universitätsmedizin Berlin, where he worked on EHR-based early warning scores for ICU settings. He also worked on trustworthy AI methods at Fraunhofer IKS in Munich and as a medical statistician at Sensyne Health in Oxford. He holds a PhD in Health Data Science from University College London.

Selected publications

• McDermott MBA, Steinberg E, Fries JA, et al. MEDS — An Emerging Data Standard and Ecosystem for Health AI Research. NEJM AI. 2026. https://doi.org/10.1056/AIra2501253
• Do DK, Rockenschaub P, Boie SD, et al. The Impact of Evaluation Strategy on Sepsis Prediction Model Performance Metrics in Intensive Care Data: Retrospective Cohort Study. J Med Internet Res. 2026. https://doi.org/10.2196/72083
• Rockenschaub P, Akay EM, Carlisle BG, et al. External validation of AI-based scoring systems in the ICU: a systematic review and meta-analysis. BMC Med Inform Decis. 2025. doi: https://doi.org/10.1186/s12911-024-02830-7
• Rockenschaub P, Hilbert A, Kossen T, et al. The Impact of Multi-Institution Datasets on the Generalizability of Machine Learning Prediction Models in the ICU. Crit Care Med. 2024. doi: 10.1097/CCM.0000000000006359
• van de Water R, Schmidt H, Elbers P, et al. Yet Another ICU Benchmark: A Flexible Multi-Center Framework for Clinical ML. The Twelfth International Conference on Learning Representations (ICLR). 2024. Available: https://openreview.net/forum?id=ox2ATRM90I
• Rockenschaub P, Xian Z, Zamanian A, et al. Robust prediction under missingness shift. arXiv. 2024. Available: https://arxiv.org/abs/2406.16484
• Rockenschaub P, Gill M, McNulty D, et al. Can the application of machine learning to electronic health records guide antibiotic prescribing decisions for suspected urinary tract infection in the Emergency Department? PLOS Dig Health. 2023. doi: https://doi.org/10.1371/journal.pdig.0000261
• Shallcross L, Rockenschaub P, Blackburn R, et al. Antibiotic prescribing for lower urinary tract infection in elderly patients in primary care and risk of bloodstream infection: a cohort study using electronic health records from England. PLOS Med. 2020;17: e100336. doi: https://doi.org/10.1371/journal.pmed.1003336