MétaCan
Menu
Back to cohort
Record W6888961538 · doi:10.24433/co.8645257.v1

Case-Base Neural Network: survival analysis with time-varying, higher-order interactions

2024· other· en· W6888961538 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueCode Ocean · 2024
Typeother
Languageen
FieldMedicine
TopicRetinal Imaging and Analysis
Canadian institutionsUniversity of ManitobaMcGill University
Fundersnot available
KeywordsCensoring (clinical trials)Set (abstract data type)ComputationArtificial neural networkSurvival analysisHyperparameterFunction (biology)Proportional hazards model

Abstract

fetched live from OpenAlex

Note that this capsule does not reproduce the exact analysis found in the manuscript, as the computation time required is greater than 10 hours. The online version tests a fast hyperparameter set (only 1 set) and performs 2 fold bootstrap on the training set. The result it produces is not useful beyond making sure the code runs. If the user wants to reproduce the analysis, they must edit the code/run.sh script. Namely, set epo=2000 (default), iterations=100 (default) and quickGrid=0 (default). We recommend running the capsule with said modifications locally due to time restrictions on codeocean. feel free to contact us if you have any issues. Case-Base Neural Networks (CBNNs) estimate the full hazard function. It naturally accounts for censoring and predicts smooth-in-time risk functions. Uses a simple objective function and models time-varying effects by design, unlike competing methods. CBNNs outperform the competing models in a simulation and two studies, with competitive performance in a third study.

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.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Insufficient payload (model declined to judge)
Consensus categoriesInsufficient payload (model declined to judge)
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: Not applicable
GenreCandidate signal: Other · Consensus signal: Other
Teacher disagreement score0.062
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0010.002
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0090.001

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 head0.024
GPT teacher head0.300
Teacher spread0.277 · 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