Biography

Patrick is a data scientist with a research focus on deriving actionable insight from large and complex healthcare data. He is particularly interested in creating and evaluating clinical decision support tools that readily translate into clinical practice and help doctors make informed decisions. Currently, Patrick is working on the Austrian Digital Heart Program, which validates the efficacy of app-based screening for atrial fibrillation.

Patrick received an MSc and PhD in Health Data Science from University College London. Following his PhD, Patrick was awarded a postdoctoral fellowship by the Alexander von Humboldt-Foundation to work on generalizable deep learning for medical risk prediction at Charité – Universitätsmedizin Berlin. Before coming to Innsbruck, Patrick spent some time as a senior researcher at Fraunhofer in Munich where he worked on statistical methods for handling the high levels of missing data often found in routine medical data.

Selected publications

• Shallcross L, Rockenschaub P, Blackburn R, Nazareth I, Freemantle N, Hayward A. Antibiotic prescribing for lower UTI in elderly patients in primary care and risk of bloodstream infection: A cohort study using electronic health records in England. PLoS Med. 2020 Sep 21;17(9):e1003336.
• Rockenschaub P, Gill MJ, McNulty D, Carroll O, Freemantle N, Shallcross L. Can the application of machine learning to electronic health records guide antibiotic prescribing decisions for suspected urinary tract infection in the Emergency Department? PLOS Digit Health. 2023 Jun 13;2(6):e0000261.
• Van de Water R, Schmidt H, Elbers P, Thoral P, Arnrich B, Rockenschaub P. Yet Another ICU Benchmark: A Flexible Multi-Center Framework for Clinical ML (Conference paper). ICLR 2024.
• Fletcher RA, Rockenschaub P, Neuen BL, Walter IJ, Conrad N, Mizani MA, Bolton T, Lawson CA, Tomlinson C, Logothetis SB, Petitjean C, Brizzi LF, Kaptoge S, Raffetti E, Calvert PA, Di Angelantonio E, Banerjee A, Mamas MA, Squire I, Denaxas S, McDonagh TA, Sudlow C, Petersen SE, Chertow GM, Khunti K, Sundström J, Arnott C, Cleland JGF, Danesh J, McMurray JJV, Vaduganathan M, Wood AM; CVD-COVID-UK/COVID-IMPACT Consortium. Contemporary epidemiology of hospitalised heart failure with reduced versus preserved ejection fraction in England: a retrospective, cohort study of whole-population electronic health records. Lancet Public Health. 2024 Nov;9(11):e871-e885.
• Rockenschaub P, Hilbert A, Kossen T, Elbers P, von Dincklage F, Madai VI, Frey D. The Impact of Multi-Institution Datasets on the Generalizability of Machine Learning Prediction Models in the ICU. Crit Care Med. 2024 Nov 1;52(11):1710-1721. d