MétaCan
Menu
Back to cohort
Record W4212897755 · doi:10.1016/s2589-7500(21)00270-3

Development and validation of an ensemble machine learning framework for detection of all-cause advanced hepatic fibrosis: a retrospective cohort study

2022· article· en· W4212897755 on OpenAlexafffundabout
Soren Sabet Sarvestany, Jeffrey C. Kwong, Amirhossein Azhie, Victor Dong, Orlando Cerocchi, Ahmed Ali, Ravikiran S. Karnam, Hadi Kuriry, Mohamed Shengir, Elisa Candido, Raquel Duchen, Giada Sebastiani, Keyur Patel, Anna Goldenberg, Mamatha Bhat

Bibliographic record

VenueThe Lancet Digital Health · 2022
Typearticle
Languageen
FieldMedicine
TopicLiver Disease Diagnosis and Treatment
Canadian institutionsVector InstituteMcGill University Health CentreMcGill UniversityToronto General HospitalUniversity of TorontoUniversity Health NetworkSickKids FoundationPublic Health Ontario
FundersFonds de Recherche du Québec - SantéInstitute for Clinical Evaluative SciencesMinistry of Health -SingaporeSick Kids FoundationUniversity Health Network
KeywordsRandom forestArtificial intelligenceTransient elastographyReceiver operating characteristicMedicineCirrhosisMachine learningGradient boostingLogistic regressionRetrospective cohort studySupport vector machineFatty liverHepatic fibrosisHepatologyInternal medicineFibrosisElastographyLiver biopsyArtificial neural networkEnsemble learningComputer scienceBiopsyDiseaseRadiologyLiver fibrosisUltrasound

Abstract

fetched live from OpenAlex

OpenAlex records an abstract for this work, but it could not be fetched just now.

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)0.017
metaresearch head score (Gemma)0.016
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: Observational
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.017
Threshold uncertainty score0.091

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0170.016
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0020.001
Science and technology studies0.0010.000
Scholarly communication0.0010.001
Open science0.0010.001
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0010.000

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 head0.035
GPT teacher head0.330
Teacher spread0.295 · 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 designObservational
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

Citations39
Published2022
Admission routes3
Has abstractyes

Explore more

Same venueThe Lancet Digital HealthSame topicLiver Disease Diagnosis and TreatmentFrench-language works237,207