Dr Andreas Karwath

Dr Andreas Karwath

Institute of Cancer and Genomic Sciences
Associate Professor

Contact details

Address
Department of Cancer and Genomic Sciences
University of Birmingham
Edgbaston
Birmingham
B15 2TT
UK

My research interests focus on the integration of clinical data and the extraction of information and patterns from this combined information source using modern AI techniques, such as variational autoencoders (VAEs). Furthermore, I am interested in cancer risk prediction, application of AI to Diabetes and clinical procedures, predictive toxicology, and the application of learning to rank, predictive toxicology. 

I am the deputy programme lead for the MSc in Health Data Science and responsible for a number of modules within the programme.

Qualifications

  • PhD, Machine Learning/Comp. Biology, University of Wales, Aberystwyth, UK
  • BSc (Hons.), Mathematics & Computing, University of Glamorgan, UK
  • Dipl.Math. (FH), Mathematics, Hochschule für Technik, Stuttgart, Germany

Biography

Dr Karwath has studied applied Mathematics in the UK and Germany and received his PhD in Computer Science from the University of Aberystwyth (UK). He has held a number of positions in Freiburg (Germany) and Mainz (Germany) before joining the University of Birmingham (UK).

Teaching

MSc Health Data Science

  • Deputy-programme lead
  • Module 1: Foundations of Computing Practices in Health Data Science
  • Module 6: Integrative Multimodal Data Analytics
  • Module 7: Interdisciplinary Health Data Research Project

MSc Health Data Science (Dubai) 

Module 1: Foundations of Computing Practices in Health Data Science

Postgraduate supervision

I am always looking for interested and motivated PhD students within my preferred research areas. Please contact me directly via email. 

Research

My main research areas are concerned with the application of Machine Learning/Artificial Intelligence and Data Mining to a variety of fields within health data and other life sciences. Apart from medical and clinical health data science, this includes Bioinformatics and Cheminformatics. From a Computer Science perspective, I am interested in structured as well as unstructured data and the fusion of different data types.

Publications

A full list of publications can be found on ORCID 

Selected publications:

 M. Wehr et al., RespiraTox – Development of a QSAR model to predict human respiratory irritants, Regulatory Toxicology and Pharmacology, DOI: 10.1016/j.yrtph.2021.105089, 2022 

A. Lorenc et al., Clinicians' Views of Patient-initiated Follow-up in Head and Neck Cancer: a Qualitative Study to Inform the PETNECK2 Trial, Clinical Oncology, DOI: 0.1016/j.clon.2021.11.010, 2022 

A. Karwath et al., Redefining β-blocker response in heart failure patients with sinus rhythm and atrial fibrillation: a machine learning cluster analysis, Lancet, DOI: 10.1016/S0140-6736(21)01638-X, 2021 

L. Slater et al., Towards similarity-based differential diagnostics for common diseases, Computers in Biology and Medicine, DOI: 10.1016/j.compbiomed.2021.104360, 2021 

K. Bunting et al., Improving the diagnosis of heart failure in patients with atrial fibrillation. Heart (British Cardiac Society), DOI: 10.1136/heartjnl-2020-318557, 2021 

E. Carr et al., Evaluation and improvement of the National Early Warning Score (NEWS2) for COVID-19: a multi-hospital study, BMC Medicine, DOI: 10.1186/s12916-020-01893-3, 2021 

H Wu et al., Ensemble learning for poor prognosis predictions: a case study on SARS-CoV2, Journal of the American Medical Informatics Association, DOI: 10.1093/jamia/ocaa295, 2020 

M. Köppel et al., Pairwise Learning to Rank by Neural Networks Revisited: Reconstruction, Theoretical Analysis and Practical Performance, Machine Learning and Knowledge Discovery in Databases, DOI: 10.1007/978-3-030-46133-1_15, 2020 

S. Altubai et al., Ontology-based prediction of cancer driver genes, Scientific Reports, DOI: 10.1038/s41598-019-53454-1, 2019 

A. Karwath et al., Convolutional Neural Networks for the Identification of Regions of Interest in PET Scans: A Study of Representation Learning for Diagnosing Alzheimer’s Disease, Conference on Artificial Intelligence in Medicine in Europe, DOI: 10.1007/978-3-319-59758-4_36, 2017

View all publications in research portal