Tasks

Information Extraction

2013 Named Entity Recognition in English clinical reports
The clinical narrative is abundant in mentions of clinical conditions, anatomical sites, medications, and procedures. This tasks consists of (a) discovering the mention boundaries and (b) mapping each mention to a UMLS CUI
Details
Normalization of acronyms/abbreviations
Many of the terms found in clinical documents are acronyms or abbreviations that can be difficult for patients to understand. This task consists of mapping pre-annotated acronym/abbreviation mention to UMLS CUIs.
2014 Information Extraction from Clinical Text
For this task, participants will be provided an empty template for each disease/disorder mention; each template consists of the mention’s UMLS CUI, mention boundaries, and unfilled attribute: value slots. Participants are asked to develop attribute classifiers that predict the value for each each attribute:value slot for the provided disease/disorder mention.
Details
2015 Clinical Named Entity Recognition
The CLEFeHealth 2015 Task 1b addresses clinical named entity recognition in languages other than English. The aim is to automatically identify clinically relevant entities in medical text in French.
Details
2016 Clinical Named Entity Recognition
The clinical narrative is abundant in mentions of clinical conditions, anatomical sites, medications, and procedures. This tasks consists of (a) discovering the mention boundaries and (b) mapping each mention to a UMLS CUI
Details
Information Extraction from Death Deports
Many of the terms found in clinical documents are acronyms or abbreviations that can be difficult for patients to understand. This task consists of mapping pre-annotated acronym/abbreviation mention to UMLS CUIs.Participants are challenged with the extraction of causes of death from a new corpus of French death reports. This task can naturally be treated as a named entity recognition and normalization task, but also as a text classification task.
Details

Information Management

2014 Visual-Interactive Search and Exploration of eHealth Data
The task challenges participants to design interactive visualisations that help patients better understand their discharge summaries and explore additional relevant documents in light of a large document corpus and their various facets in context.
Details
2015 Clinical Speech Recognition
The aim is to convert verbal nursing handover to written free-text records. We challenge the participants to minimize word-detection errors by: (1) addressing the correctness of the speech recognition engine itself and/or (2) improving this through post-processing methods for the recognised text.
Details
2016 Handover Information Extraction
This task addresses clinical information extraction related to Australian nursing shift changes. This extends the 2015 task of converting verbal nursing handover to written free-text records; we challenge participants to maximise the correctness in structuring these written free-text records by pre-filling a handover form by automatically identifying relevant text-snippets for each slot of the form.
Details

Information Retrieval

2013-2016 Patient-centered Information Retrieval
This task aims to evaluate the effectiveness of information retrieval systems when searching for health content on the web, with the objective to foster research and development of search engines tailored to health information seeking.
Details:2013 2014 2015 2016
2014-2016 Cross-lingual Information Retrieval
As a complementary task to the Patient-centered Information Retrieval task, this task aims at develop multilingual approaches, in order to retrieve English documents relevant to non-English queries
Details:2014 2015 2016
2016 Interactive Search
This task explores iterative query reformulation along with the associated document retrieval, with the aim of studying differences between querying strategies and how these are supported by the developed systems.
Details

Link to the original page https://sites.google.com/site/clefehealth/tasks