Book/Dissertation / PhD Thesis

FZJ-2023-02488

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png Design and Evaluation of Parallel and Scalable Machine Learning Research in Biomedical Modelling Applications

Barakat, C. (Corresponding author)FZJ*

2023
Reykjavík, Iceland
ISBN: 978-9935-9697-9-8

This record in other databases:

Please use a persistent id in citations: doi:10.34734/FZJ-2023-02488

Abstract: The use of Machine Learning (ML) techniques in the medical field is not a new occurrence and several papers describing research in that direction have been published. This research has helped in analysing medical images, creating responsive cardiovascular models, and predicting outcomes for medical conditions among many other applications. This Ph.D. aims to apply such ML techniques for the analysis of Acute Respiratory Distress Syndrome (ARDS) which is a severe condition that affects around 1 in 10.000 patients worldwide every year with life-threatening consequences. We employ previously developed mechanistic modelling approaches such as the “Nottingham Physiological Simulator,” through which better understanding of ARDS progression can be gleaned, and take advantage of the growing volume of medical datasets available for research (i.e., “big data”) and the advances in ML to develop, train, and optimise the modelling approaches. Additionally, the onset of the COVID-19 pandemic while this Ph.D. research was ongoing provided a similar application field to ARDS, and made further ML research in medical diagnosis applications possible. Finally, we leverage the available Modular Supercomputing Architecture (MSA) developed as part of the Dynamical Exascale Entry Platform~- Extreme Scale Technologies (DEEP-EST) EU Project to scale up and speed up the modelling processes. This Ph.D. Project is one element of the Smart Medical Information Technology for Healthcare (SMITH) project wherein the thesis research can be validated by clinical and medical experts (e.g. Uniklinik RWTH Aachen).

Note: Dissertation, Háskóli Íslands, 2023

---

Contributing Institute(s):

1. Jülich Supercomputing Center (JSC)

Research Program(s):

1. 5112 - Cross-Domain Algorithms, Tools, Methods Labs (ATMLs) and Research Groups (POF4-511) (POF4-511)
2. BMBF 01ZZ1803B - SMITH - Medizininformatik-Konsortium - Beitrag Universitätsklinikum Aachen (01ZZ1803B) (01ZZ1803B)
3. EUROCC - National Competence Centres in the framework of EuroHPC (951732) (951732)
4. RAISE - Research on AI- and Simulation-Based Engineering at Exascale (951733) (951733)
5. DEEP-EST - DEEP - Extreme Scale Technologies (754304) (754304)

Appears in the scientific report 2023

---

Database coverage:

---