MétaCan
Menu
Back to cohort
Record W4394769784 · doi:10.1016/j.acra.2024.02.028

Use of Response Permutation to Measure an Imaging Dataset’s Susceptibility to Overfitting by Selected Standard Analysis Pipelines

2024· article· en· W4394769784 on OpenAlexafffund
Jayasree Chakraborty, Abhishek Midya, Brenda F. Kurland, Mattea Welch, Mithat Gönen, Chaya S. Moskowitz, Amber L. Simpson

Bibliographic record

VenueAcademic Radiology · 2024
Typearticle
Languageen
FieldMedicine
TopicRadiomics and Machine Learning in Medical Imaging
Canadian institutionsQueen's UniversityUniversity Health Network
FundersNational Cancer InstituteNational Institutes of HealthQueen's University
KeywordsOverfittingArtificial intelligenceRandom forestComputer scienceSupport vector machinePattern recognition (psychology)Linear discriminant analysisMachine learningLogistic regressionSample size determinationCross-validationBootstrapping (finance)Receiver operating characteristicStatisticsData miningMathematicsArtificial neural networkEconometrics

Abstract

fetched live from OpenAlex

Rationale and ObjectivesThis study demonstrates a method for quantifying the impact of overfitting on the receiving operator characteristic curve (AUC) when using standard analysis pipelines to develop imaging biomarkers. We illustrate the approach using two publicly available repositories of radiology and pathology images for breast cancer diagnosis.Materials and MethodsFor each dataset, we permuted the outcome (cancer diagnosis) values to eliminate any true association between imaging features and outcome. Seven types of classification models (logistic regression, linear discriminant analysis, Naïve Bayes, linear support vector machines, nonlinear support vector machine, random forest, and multi-layer perceptron) were fitted to each scrambled dataset and evaluated by each of four techniques (all data, hold-out, 10-fold cross-validation, and bootstrapping). After repeating this process for a total of 50 outcome permutations, we averaged the resulting AUCs. Any increase over a null AUC of 0.5 can be attributed to overfitting.ResultsApplying this approach and varying sample size and the number of imaging features, we found that failing to control for overfitting could result in near-perfect prediction (AUC near 1.0). Cross-validation offered greater protection against overfitting than the other evaluation techniques, and for most classification algorithms a sample size of at least 200 was required to assess as few as 10 features with less than 0.05 AUC inflation attributable to overfitting.ConclusionThis approach could be applied to any curated dataset to suggest the number of features and analysis approaches to limit overfitting. This study demonstrates a method for quantifying the impact of overfitting on the receiving operator characteristic curve (AUC) when using standard analysis pipelines to develop imaging biomarkers. We illustrate the approach using two publicly available repositories of radiology and pathology images for breast cancer diagnosis. For each dataset, we permuted the outcome (cancer diagnosis) values to eliminate any true association between imaging features and outcome. Seven types of classification models (logistic regression, linear discriminant analysis, Naïve Bayes, linear support vector machines, nonlinear support vector machine, random forest, and multi-layer perceptron) were fitted to each scrambled dataset and evaluated by each of four techniques (all data, hold-out, 10-fold cross-validation, and bootstrapping). After repeating this process for a total of 50 outcome permutations, we averaged the resulting AUCs. Any increase over a null AUC of 0.5 can be attributed to overfitting. Applying this approach and varying sample size and the number of imaging features, we found that failing to control for overfitting could result in near-perfect prediction (AUC near 1.0). Cross-validation offered greater protection against overfitting than the other evaluation techniques, and for most classification algorithms a sample size of at least 200 was required to assess as few as 10 features with less than 0.05 AUC inflation attributable to overfitting. This approach could be applied to any curated dataset to suggest the number of features and analysis approaches to limit overfitting.

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 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)0.003
metaresearch head score (Gemma)0.010
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.685
Threshold uncertainty score0.998

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0030.010
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0010.003
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

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 head0.027
GPT teacher head0.360
Teacher spread0.334 · 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 teacher head, not a consensus.

Study designBench or experimental
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

Citations4
Published2024
Admission routes2
Has abstractyes

Explore more

Same venueAcademic RadiologySame topicRadiomics and Machine Learning in Medical ImagingFrench-language works237,207