BioASQ Task a on Large-Scale Online Biomedical Semantic Indexing
In this task, the participants are asked to classify new PubMed documents, before PubMed curators annotate (in effect, classify) them manually. The classes come from the MeSH hierarchy. As new manual annotations become available, they are used to evaluate the classification performance of participating systems.
In 2022 BioASQ Task a copmleted ten years of pushing the research in biomedical semantic indexing forward. During these ten years, the methods developed by participants for indexing the biomedical literature achieved significant improvements of about 10%. The high point for this task was the recent adoption of fully automated indexing by NLM in mid-2022. Therefore, ten years after its initial introduction, this task fulfilled its goal of facilitating the advancement of biomedical semantic indexing research.
BioASQ Task MedProcNER on MEDical PROCedure Named Entity Recognition
This task focuses on the detection, normalization and indexing of clinical procedures in medical documents in Spanish. Participating systems are challenged to create systems for three subtasks: (a) clinical procedure detection, (b) entity normalization to SNOMED CT and (c) whole document indexing using SNOMED CT codes.
The BioASQ Task MedPRocNER was co-ogranized with the Barcelona Supercomputing Center in 2023. Read more...
BioASQ Task DisTEMIST on Disease Text Mining and Indexing
This task focuses on the recognition and indexing of diseases in medical documents, by posing subtasks of indexing medical documents with controlled terminologies on (1) automatic detection of textual evidence, i.e. disease entity mentions in text (DisTEMIST-Entities), and (2) normalization of these disease mentions to terminologies (DisTEMIST-Linking).
The BioASQ Task DisTEMIST was co-ogranized with the Barcelona Supercomputing Center in 2022. Read more...
BioASQ Task MESINESP on Medical Semantic Indexing In Spanish
This task addresses the automatic indexing with structured medical vocabularies (DeCS terms) of documents from scientific literature (MESINESP-L), clinical trials (MESINESP-T) and patents (MESINESP-P) written in Spanish. The main aim is to promote the development of semantic indexing tools of practical relevance of non-English content, determining the current-state-of-the art, identifying challenges and comparing the strategies and results to those published for English data.
This task was introduced in 2020 with a single batch on indexing scientific literature from the IBECS and LILACS databases. In 2021, the task was extented to the indexing of clinical trials and patents as well. The BioASQ Task MESINESP was co-ogranized with the Barcelona Supercomputing Center. Read more...
BioASQ Task c on Funding Information Extraction From Biomedical Literature
In this task, the participants are asked to extract grant ids and grant agencies from the full text of PumMed documents, available in PubMed Central. Annotations from PubMed are used to evaluate the information extraction performance of participating systems. This task took place as a single test batch in 2017.
