MétaCan
Menu
Back to cohort
Record W7117247381 · doi:10.1002/epi.70058

A call for ethical, equitable, and effective artificial intelligence to improve care for all people with epilepsy: A roadmap. A report by the ILAE Global Advocacy Council and Big Data Commission

2025· article· en· W7117247381 on OpenAlexaff
Colin B. Josephson, Sándor Beniczky, Spiros Denaxas, Lara Jehi, Angelina Kakooza Mwesige, Nathalie Jetté, Gabriel Davis Jones, Philippe Ryvlin, A Sen, Chahnez Charfi Triki, G Waters, A B Guekht, J. Helen Cross

Bibliographic record

VenueEpilepsia · 2025
Typearticle
Languageen
FieldMedicine
TopicEpilepsy research and treatment
Canadian institutionsHotchkiss Brain InstituteUniversity of Calgary
FundersEisaiUniversity College LondonUCB PharmaOtsuka PharmaceuticalBritish Heart FoundationAngelini PharmaNational Institute for Health and Care ResearchEpilepsy Research UKNational Institutes of HealthLivaNova
KeywordsWorkflowBig dataCommissionEpilepsyGlobal healthHealth careWearable computereHealth

Abstract

fetched live from OpenAlex

The artificial intelligence (AI) revolution is upon us. It will inevitably form a central component of epilepsy workflows and patient advocacy. Therefore, it behooves us as health care providers to ride the crest of this wave and guide its direction for the benefit of all people with epilepsy. Emerging AI-based solutions include decision support tools, automated interpretation of electroencephalography (EEG) and brain imaging, and wearable devices that detect seizures and improve patient safety. Pipelines, including decentralized approaches and federated learning, are now being built that will democratize access and facilitate the next generation of AI tools for the global epilepsy community. Despite this, enduring issues remain incompletely addressed. For example, AI requires high volumes of data, leading to concerns about ethical ownership, stewardship, and privacy. Few AI-based tools have progressed from derivation to validation stages, and only rare exceptions undergo real-world evaluation. Inadvertent harmful algorithmic and decision allocation biases also continue to represent major risks to the global epilepsy population. Additional barriers include geographical disparities in computing resources, proprietary ownership of electronic health records, EEG, and brain-imaging platforms, and greenhouse gas emissions related to the demanding power requirements of AI. Therefore, to fully avail ourselves of the benefits of AI, we assert that ethical, equitable, and effective AI for epilepsy requires collaboration from the entirety of the global epilepsy community. Fundamental to this is early and deliberate engagement of people from low- and middle-income countries to ensure that AI-based solutions do not exacerbate existing global disparities. Ultimately, we advocate for "decision intelligence" approaches to the development of AI-based epilepsy solutions, which involves early engagement of all interest-holders to ensure that the correct questions are addressed and the right technical approaches are deployed to maximize value for the global epilepsy community.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.056
metaresearch head score (Gemma)0.065
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: none
GenreCandidate signal: Other · Consensus signal: none
Teacher disagreement score0.056
Threshold uncertainty score0.298

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0560.065
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0020.002
Bibliometrics0.0030.003
Science and technology studies0.0060.017
Scholarly communication0.0230.038
Open science0.0030.019
Research integrity0.0210.041
Insufficient payload (model declined to judge)0.0200.008

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.063
GPT teacher head0.373
Teacher spread0.311 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designTheoretical or conceptual
Domainnot available
GenreOther

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations1
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueEpilepsiaSame topicEpilepsy research and treatmentFrench-language works237,207