Richard Dobson


Experimental Evaluation and Development of a Silver-Standard for the MIMIC-III Clinical Coding Dataset
Thomas Searle | Zina Ibrahim | Richard Dobson
Proceedings of the 19th SIGBioMed Workshop on Biomedical Language Processing

Clinical coding is currently a labour-intensive, error-prone, but a critical administrative process whereby hospital patient episodes are manually assigned codes by qualified staff from large, standardised taxonomic hierarchies of codes. Automating clinical coding has a long history in NLP research and has recently seen novel developments setting new benchmark results. A popular dataset used in this task is MIMIC-III, a large database of clinical free text notes and their associated codes amongst other data. We argue for the reconsideration of the validity MIMIC-III’s assigned codes, as MIMIC-III has not undergone secondary validation. This work presents an open-source, reproducible experimental methodology for assessing the validity of EHR discharge summaries. We exemplify the methodology with MIMIC-III discharge summaries and show the most frequently assigned codes in MIMIC-III are undercoded up to 35%.

Comparative Analysis of Text Classification Approaches in Electronic Health Records
Aurelie Mascio | Zeljko Kraljevic | Daniel Bean | Richard Dobson | Robert Stewart | Rebecca Bendayan | Angus Roberts
Proceedings of the 19th SIGBioMed Workshop on Biomedical Language Processing

Text classification tasks which aim at harvesting and/or organizing information from electronic health records are pivotal to support clinical and translational research. However these present specific challenges compared to other classification tasks, notably due to the particular nature of the medical lexicon and language used in clinical records. Recent advances in embedding methods have shown promising results for several clinical tasks, yet there is no exhaustive comparison of such approaches with other commonly used word representations and classification models. In this work, we analyse the impact of various word representations, text pre-processing and classification algorithms on the performance of four different text classification tasks. The results show that traditional approaches, when tailored to the specific language and structure of the text inherent to the classification task, can achieve or exceed the performance of more recent ones based on contextual embeddings such as BERT.


MedCATTrainer: A Biomedical Free Text Annotation Interface with Active Learning and Research Use Case Specific Customisation
Thomas Searle | Zeljko Kraljevic | Rebecca Bendayan | Daniel Bean | Richard Dobson
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP): System Demonstrations

An interface for building, improving and customising a given Named Entity Recognition and Linking (NER+L) model for biomedical domain text, and the efficient collation of accurate research use case specific training data and subsequent model training. Screencast demo available here:


The language of mental health problems in social media
George Gkotsis | Anika Oellrich | Tim Hubbard | Richard Dobson | Maria Liakata | Sumithra Velupillai | Rina Dutta
Proceedings of the Third Workshop on Computational Linguistics and Clinical Psychology