Joeky Senders

17 General introduction and thesis outline relative performance and utility for medical text analysis. Chapter 8 compares the learning curves of various algorithms in determining the histopathological diagnosis of brain tumor patients based on free-text pathology reports. These learning curves elucidate the learning efficiency of various algorithms, as well as the yield of natural language processing in clinical research. Furthermore, a modified deep learning architecture is developed in this chapter and its performance compared to conventional deep learning architectures and regression-based algorithms. Summary and general discussion Chapter 9 synthesizes the most important findings of the current thesis. Chapter 10 addresses the implications of these finding with regards to the clinical care of neurosurgical and neuro-oncological patients. It provides recommendations for future machine learning research in healthcare. All custom computer code and software developed throughout this thesis have been made publicly-available and their associated URL-links can be found in the Open-source code and software appendix .