ACCUMULATE automatically recognizes crucial information in the free text of clinical reports written in English and Dutch by designing, developing and evaluating advanced language technology for deep semantic processing of the texts which are often morpho-syntactically not well-formed. An extra focus is on easy portability of the technology across domains and languages.
We have built novel deep learning models for recognizing temporal and causal relations between medical events in the natural language texts of clinical records. We are investigating explainable deep learning models for medical decision making in clinical radiology. In addition, we study algorithms for hierarchical classification of clinical reports with ICD (International Classification of Diseases) coding. We have built models for extracting event time lines from clinical reports.