Patrick Schrempf

Patrick Schrempf serves as an Honorary Research Fellow at the School of Computer Science, University of St Andrews, with research expertise spanning medical image analysis and natural language processing applications. His work bridges clinical informatics and machine learning, focusing particularly on extracting meaningful information from medical reports and imaging data. Previously, he worked as a Research Engineer at Canon Medical Research Europe Ltd from August 2018 to August 2022.

His educational background includes:

• Bachelor of Science in Computer Science, University of St Andrews (awarded June 27, 2018)
• Doctor of Engineering (DEng), University of St Andrews (thesis completed June 14, 2023)

Schrempf's research interests center around applying machine learning techniques to healthcare challenges, with particular emphasis on medical imaging analysis, natural language processing for clinical text, and epidemic prediction systems. His work integrates attention mechanisms, ontological frameworks, and multi-label classification approaches to solve complex problems in radiology report analysis and clinical data extraction. He has made significant contributions to developing systems that improve the efficiency and accuracy of medical data processing through expert-guided learning approaches.

An analysis of his publication record reveals a strong focus on medical applications of machine learning, particularly in radiology report processing where he has developed innovative attention-based models for multi-label extraction. His research demonstrates progression from foundational work in radar-based interaction systems toward increasingly specialized medical applications, with a consistent thread of attention mechanisms and ontology integration throughout his publications. The temporal pattern shows growing specialization in medical informatics applications since 2019.

His notable recognition includes:

• Best Paper Award at LABELS workshop, MICCAI 2020 for his work on multi-label extraction from radiology reports

Schrempf has collaborated extensively with researchers from Canon Medical Research Europe and other academic institutions, particularly on projects involving medical image analysis and clinical text processing. His doctoral thesis on "NLP-supervised stroke detection in medical images" represents a significant contribution to the field of medical AI, building upon his earlier work in radiology report analysis. His research has garnered attention across academic platforms with substantial Mendeley readership and mentions in various academic networks.

His work contributes to UN Sustainable Development Goals related to good health and well-being through advanced medical imaging and analysis techniques.