MétaCan
Menu
Back to cohort
Record W3209901185 · doi:10.1016/s2589-7500(21)00208-9

The false hope of current approaches to explainable artificial intelligence in health care

2021· review· en· W3209901185 on OpenAlexaff
Marzyeh Ghassemi, Luke Oakden‐Rayner, Andrew L. Beam

Bibliographic record

VenueThe Lancet Digital Health · 2021
Typereview
Languageen
FieldComputer Science
TopicExplainable Artificial Intelligence (XAI)
Canadian institutionsVector Institute
FundersNational Heart, Lung, and Blood Institute
KeywordsTransparency (behavior)Argument (complex analysis)Process (computing)Black boxComputer scienceWorkforceHealth careArtificial intelligencePsychologyRisk analysis (engineering)MedicinePolitical scienceComputer securityLaw

Abstract

fetched live from OpenAlex

The black-box nature of current artificial intelligence (AI) has caused some to question whether AI must be explainable to be used in high-stakes scenarios such as medicine. It has been argued that explainable AI will engender trust with the health-care workforce, provide transparency into the AI decision making process, and potentially mitigate various kinds of bias. In this Viewpoint, we argue that this argument represents a false hope for explainable AI and that current explainability methods are unlikely to achieve these goals for patient-level decision support. We provide an overview of current explainability techniques and highlight how various failure cases can cause problems for decision making for individual patients. In the absence of suitable explainability methods, we advocate for rigorous internal and external validation of AI models as a more direct means of achieving the goals often associated with explainability, and we caution against having explainability be a requirement for clinically deployed models.

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)0.020
metaresearch head score (Gemma)0.035
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: none
GenreCandidate signal: Review · Consensus signal: Review
Teacher disagreement score0.020
Threshold uncertainty score0.105

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0200.035
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0020.002
Bibliometrics0.0040.004
Science and technology studies0.0010.011
Scholarly communication0.0050.009
Open science0.0030.004
Research integrity0.0050.010
Insufficient payload (model declined to judge)0.0040.001

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 head0.374
GPT teacher head0.419
Teacher spread0.045 · 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 designNot applicable
Domainnot available
GenreReview

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

Citations1,361
Published2021
Admission routes1
Has abstractyes

Explore more

Same venueThe Lancet Digital HealthSame topicExplainable Artificial Intelligence (XAI)French-language works237,207