MétaCan
Menu
Back to cohort
Record W3125451872 · doi:10.15353/jcvis.v6i1.3548

Where do Clinical Language Models Break Down? A Critical Behavioural Exploration of the ClinicalBERT Deep Transformer Model

2021· article· en· W3125451872 on OpenAlexafffundvenue
Alexander MacLean, Alexander Wong

Bibliographic record

VenueJournal of Computational Vision and Imaging Systems · 2021
Typearticle
Languageen
FieldMedicine
TopicArtificial Intelligence in Healthcare and Education
Canadian institutionsUniversity of Waterloo
FundersUniversity of Waterloo
KeywordsComputer scienceTransformerInferenceArtificial intelligenceLanguage modelLeverage (statistics)RealmDeep learningEncoderLanguage understandingMachine learningData scienceNatural language processingEngineering

Abstract

fetched live from OpenAlex

The introduction of Bidirectional Encoder Representations from Transformers (BERT) was a major breakthrough for transfer learning in natural language processing, enabling state-of-the-art performance across a large variety of complex language understanding tasks. In the realm of clinical language modeling, the advent of BERT led to the creation of ClinicalBERT, a state-of-the-art deep transformer model pretrained on a wealth of patient clinical notes to facilitate for downstream predictive tasks in the clinical domain. While ClinicalBERT has been widely leveraged by the research community as the foundation for building clinical domain-specific predictive models given its overall improved performance in the Medical Natural Language inference (MedNLI) challenge compared to the seminal BERT model, the fine-grained behaviour and intricacies of this popular clinical language model has not been well-studied. Without this deeper understanding, it is very challenging to understand where ClinicalBERT does well given its additional exposure to clinical knowledge, where it doesn't, and where it can be improved in a meaningful manner. Motivated to garner a deeper understanding, this study presents a critical behaviour exploration of the ClinicalBERT deep transformer model using MedNLI challenge dataset to better understanding the following intricacies: 1) decision-making similarities between ClinicalBERT and BERT (leverage a new metric we introduce called Model Alignment), 2) where ClinicalBERT holds advantages over BERT given its clinical knowledge exposure, and 3) where ClinicalBERT struggles when compared to BERT. The insights gained about the behaviour of ClinicalBERT will help guide towards new directions for designing and training clinical language models in a way that not only addresses the remaining gaps and facilitates for further improvements in clinical language understanding performance, but also highlights the limitation and boundaries of use for such 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)0.007
metaresearch head score (Gemma)0.042
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.008
Threshold uncertainty score0.038

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0070.042
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.001
Science and technology studies0.0010.002
Scholarly communication0.0030.007
Open science0.0020.003
Research integrity0.0020.006
Insufficient payload (model declined to judge)0.0050.002

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 head0.177
GPT teacher head0.487
Teacher spread0.310 · 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 designSimulation or modeling
Domainnot available
GenreEmpirical

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

Citations2
Published2021
Admission routes3
Has abstractyes

Explore more

Same venueJournal of Computational Vision and Imaging SystemsSame topicArtificial Intelligence in Healthcare and EducationFrench-language works237,207