BioASQ organizes challenges on biomedical semantic indexing and question answering (QA). The challenges include tasks relevant to hierarchical text classification, machine learning, information retrieval, QA from texts and structured data, multi-document summarization and many other areas.

Monetary and other prizes are awarded to the best performing systems.

 

What is your area of expertise?

Find out how your research interests relate to the BioASQ challenges.

The Challenge

In 2025, the thirteenth BioASQ challenge comprises the following tasks.

Running tasks

BioASQ Task b on Biomedical Semantic QA (involves IR, QA, summarization and more)

  • The organizers distribute English biomedical questions written by biomedical experts.
  • The participants provide: relevant articles, snippets, “exact” answers (e.g. named entities), and “ideal” answers (paragraph-sized summaries).
  • Evaluation: both automatic (GMAP, MRR, ROUGE etc.) and manual (by experts).

The process of task B on Biomedical Question Answering.


BioASQ Task Synergy on Biomedical Semantic QA for developing issues

  • The organizers distribute open questions on developing biomedical topics.
  • The participants provide: relevant articles, snippets, “exact” answers, and “ideal” answers.
  • The biomedical experts assess the responses and provide feedback to the participants to improve their responses.
  • Evaluation: both automatic (GMAP, MRR, ROUGE etc.) and manual (by experts).

The process of task Synergy on Biomedical Question Answering for Develiping Topics.


BioASQ Task MultiClinSum on Multilingual Clinical Summarization

  • The organizers distribute lengthy clinical case reports written in English, Spanish, French, and Portuguese.
  • The participants generate summaries of the clinical case reports.
  • Evaluation: based on comparison with manual summaries of the clinical case reports.

The BioASQ Task MultiClinSum is co-ogranized with the Barcelona Supercomputing Center.


BioASQ Task BioNNE-L on Nested Named Entity Linking in Russian and English

  • The organizers distribute biomedical articles in Russian and English with nested named entity mentions.
  • The participants normalize the entity mentions to concept names and unique UMLS identifiers.
  • Evaluation: based on comparison with manual nested named entity linking annotations.

The BioASQ Task BioNNE-L is co-ogranized with the Kazan Federal University.


BioASQ Task ElCardioCC on Clinical Coding in Cardiology

  • The organizers distribute discharge letters from Greek hospitals.
  • The participants assign cardiology-related ICD-10 codes and extract specific concept mentions.
  • Evaluation: based on comparison with manual ICD-10 annotations.

The BioASQ Task ElCardioCC is co-ogranized with the Aristotle University of Thessaloniki.


BioASQ Task GutBrainIE on Gut-Brain interplay Information Extraction

  • The organizers distribute PubMed abstracts discussing the gut-brain interplay.
  • The participants extract named entities, link them to concepts in a reference ontology, and identify binary relations between entity pairs.
  • Evaluation: based on comparison with manual annotations.

The BioASQ Task GutBrainIE is co-ogranized with the University of Padua.

Read more