CLEF eHealth 2017


Lab Overview

Programme CLEF eHealth 2017:

Session 1, Tuesday, 9am-11am in Swift Theatre – Lab Overview – Chair Liadh Kelly

9.00-9.15: Workshop welcome

9.15-10.05: Keynote  Juliane Fluck, Fraunhofer, Germany – BioCreative and beyond: text mining for biocuration and medical data integration (40+10)

10.05-11.25: Tasks 1 Overview

10.25-11.45: Tasks 2 Overview

10.45-11.05: Tasks 3 Overview

Session 2  –  Tuesday, 2.00-4.00pm in Room 5039 – Task 2 (TAR task)  – Chair Evangelos Kanoulas

14.00-16.00: TAR (Task 2) session: 

14:00 – 15:30 (e-Health TAR participant’s presentations)

  1. Allard J. van Altena, Amsterdam Medical Center (AMC)
  2. Athanasios Lagopoulos, Aristotle University of Thessaloniki (AUTH) [Presentation]
  3. Christopher Norman, Centre Nationnal de la Recherche Scientifique & Amsterdam Medical Center (CNRS) 
  4. Noah Hollmann, Eidgenoessische Technische Hochschule Zurich (ETH) 
  5. Zhe Yu, North Carolina State University (NCSU) 
  6. Giorgio Maria Di Nunzio, University of Padua (Padua) 
  7. Amal H Alharbi, University of Sheffield (Sheffield) 
  8. Gaurav Singh, University College London & Northeastern University (UCL) 
  9. Harry Scells, Queensland University of Technology & CSIRO (QUT) 
  10. Leif Azzopardi, University of Strathclyde (UOS)

15:30 – 16:00 (e-Health TAR reflection/next year)

16:00 – 16:30 (TAR e-Health poster session)

Session 3  –  Tuesday, 4.30-6.30pm in Room 5039 – Task 1 (IE task)- Chair Aurélie Névéol

16:30 Giorgio Di Nunzio: A Lexicon Based Approach to Classification of ICD10 Codes. IMS Unipd at CLEF eHealth Task 1

16:45 Elena Tutubalina: KFU at CLEF eHealth 2017 Task 1: ICD-10 Coding of English Death Certificates with Recurrent Neural Networks

17:00 Lydia-Mai Hodac: LITL at CLEF eHealth2017: Automatic Classification of Death Reports

17:15 Thomas Lavergne: Multiple Methods for Multi-class, Multi-label ICD-10 Coding of Multi-granularity, Multilingual Death Certificates

17:30 Andon Tchechmedjiev: ICD10 Coding of Death Certificates with the NCBO and SIFR Annotators at CLEF eHealth 2017 Task 1

17:45 Jurica Seva: Multi-lingual ICD-10 Coding using a Hybrid rule-based and Supervised Classification Approach at CLEF eHealth 2017

18:00 Aude Robert: Findings of the replication track

18:15 Discussion on the future of information extraction at CLEF

Session 4 , Wednesday, 1.45pm-3.45pm in Galbraith Room (long room hub) – Task 3 (IR task) – Chair Guido Zuccon

15mins – Presentation 1: Manuel Carlos Díaz Galiano – Team SINAI, Universidad de Jaen

15mins – Presentation 2: Hua Yang, Team UEvora, Universidade de Evora 

15mins – Presentation 3: Tebo Leburu-Dingalo, Team ub-botswana, University of Botswana 

15mins – Presentation 4: Shadi Saleh, Team CUNI, Charles University in Prague 

15mins – Presentation 5: Heung-Seon Oh, Team KISTI, Korean Institute of Science and Technology Information  [TBC]

15mins – Presentation 6: Guido Zuccon, (Organisers runs) Team IELAB, Queensland University of Technology + Team TUW, Vienna University of Technology

15mins – Discussion on the future of the task

15mins – Wrapup of CLEF eHealth & open discussion – Chair Lorraine Goeuriot

<break with poster session>

Did you take part in a past CLEF eHealth lab? Are you using our datasets? 

Share your thoughts!

Problem: Laypeople find eHealth documents to be difficult to understand and also clinicians have problems in understanding the jargon of other professional groups even though laws and policies emphasise the need to document care in a comprehensive manner and provide further information on health conditions to help their understanding. A simple example from a US discharge document is “AP: 72 yo f w/ ESRD on HD, CAD, HTN, asthma p/w significant hyperkalemia & associated arrythmias.”
However, authors of both care documents and consumer leaflets are overloaded with information and face many challenges in the timely and efficient generation, processing and sharing of such information. One example here is clinical handover between nurses, where verbal handover and note taking can lead to loss of information and electronic documentation is laborious, taking time away from patient education. Coupled with this the use of the Web as source of health-related information is a widespread phenomenon. Search engines are commonly used as a means to access health information available online, however, the reliability, quality and suitability of the information for the target audience varies greatly. On top of this individuals’ abilities to express their information needs, and indeed their expression styles, vary greatly.
Previous research has shown that exposing people with no or scarce medical knowledge to complex medical language may lead to erroneous self-diagnosis and self-treatment and that access to medical information on the Web can lead to the escalation of concerns about common symptoms (e.g., cyberchondria). Research has also shown that current commercial search engines are yet far from being effective in answering such queries. Further research needs to be carried out in order to provide solutions to these problems. CLEF eHealth aims at providing datasets and gathering researchers working on related topics. 

Usage scenario: is to ease and support patients, their next-of-kins and clinical staff in understanding, accessing and authoring eHealth information in a multilingual setting. eHealth documents are much easier to understand after expanding shorthand, correcting the misspellings, normalising all health conditions to standardised terminology, and linking the words to a patient-centric search on the Internet. This would result in “Description of the patient’s active problem: 72 year old female with dependence on hemodialysis, coronary heart disease, hypertensive disease, and asthma who is currently presenting with the problem of significant hyperkalemia and associated arrhythmias” with the highlighted words linked to their definitions in Consumer Health Vocabulary and other patient-friendly sources. Further, providing the required eHealth information in response to our target user groups information needs in a timely manner, where this information is reliable, accurate and available in a multilingual setting is crucial. In addition, auto converting a verbal nursing handover to text and then highlighting important information within the transcription for the next nurse would aid care documentation and release nurses time to, for example, discuss these resources and provide further information for a longer time with the patients.

This year, CLEF eHealth organises 3 tasks:

Task 1. Multilingual Information Extraction

Task 2. Technologically Assisted Reviews in Empirical Medicine <new task!>

Task 3. Patient-centred information retrieval 

This year CLEF eHealth also offers a student mentoring track. Contact the lab chairs if you are interested in taking part in this track. <new!>

Learn more about CLEF eHealth 2013-2017!