MétaCan
Menu
Back to cohort

On the Equivalence of Classic ROC Analysis and the Loss-function Model to Set Cut Points in Sequential Testing

2003· article· en· W2052345280 on OpenAlexaff
Glenn Regehr, Jerry A. Colliver

Bibliographic record

VenueAcademic Medicine · 2003
Typearticle
Languageen
FieldEngineering
TopicIndustrial Vision Systems and Defect Detection
Canadian institutionsUniversity of TorontoUniversity Health Network
Fundersnot available
KeywordsEquivalence (formal languages)Cut-pointSet (abstract data type)StatisticsMathematicsFunction (biology)Receiver operating characteristicComputer scienceArtificial intelligenceDiscrete mathematicsBiology

Abstract

fetched live from OpenAlex

In an effort to reduce the cost of administration for objective structured clinical examinations (OSCEs), several authors have promoted the use of sequential testing in which all candidates take a short screening test and candidates who pass the screen are exempted from taking the full test. Traditionally, the determination of the optimally efficient cut point (passing score) for the screen has used ROC analysis to minimize false-positive and false-negative errors. Recently, Muijtjens et al. have questioned the appropriateness of the ROC method for these purposes and have promoted an alternative method that uses a "loss" formula. However, given certain theoretically derived conditions, it can be shown that the use of the loss formula is functionally identical to using ROC analysis, and the authors suggest that continued use of the ROC method is appropriate.

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)0.098
metaresearch head score (Gemma)0.250
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: Theoretical or conceptual
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.098
Threshold uncertainty score0.518

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0980.250
Meta-epidemiology (narrow)0.0030.001
Meta-epidemiology (broad)0.0040.002
Bibliometrics0.0050.003
Science and technology studies0.0010.010
Scholarly communication0.0040.008
Open science0.0040.005
Research integrity0.0050.006
Insufficient payload (model declined to judge)0.0020.001

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 head0.075
GPT teacher head0.298
Teacher spread0.223 · 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
GenreMethods

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

Citations5
Published2003
Admission routes1
Has abstractyes

Explore more

Same venueAcademic MedicineSame topicIndustrial Vision Systems and Defect DetectionFrench-language works237,207