MétaCan
Menu
Back to cohort
Record W4403090795 · doi:10.1101/2024.10.02.24314783

Inconsistency detection in cancer data classification using explainable-AI

2024· preprint· en· W4403090795 on OpenAlexaff
Pouria Mortezaagha, Arya Rahgozar

Bibliographic record

VenuemedRxiv · 2024
Typepreprint
Languageen
FieldComputer Science
TopicTopic Modeling
Canadian institutionsUniversity of OttawaOttawa Hospital
Fundersnot available
KeywordsComputer scienceArtificial intelligenceCancer detectionCancerMachine learningPattern recognition (psychology)MedicineInternal medicine

Abstract

fetched live from OpenAlex

A bstract This paper presents a novel approach to improving text-based cancer data classification by integrating BERTopic clustering with Support Vector Machine (SVM) classifiers, combined with the Explainable Inconsistency Algorithm (EIA). The proposed method leverages advanced preprocessing techniques, including Node2Vec embeddings, to enhance both clustering and classification performance. Through the introduction of EIA, we automatically identify and eliminate outliers and discordant data points, thus improving classification accuracy and providing valuable insights into underlying data relation-ships. A key innovation in this work is the use of recommender systems for mapping clusters to labels, which improves label assignment through collaborative filtering techniques. Our experimental results show a significant increase in both accuracy and F1-score after addressing data inconsistencies, with improvements validated through statistical tests, including t-tests. This paper contributes a robust, explainable, and scalable framework for cancer data analysis, offering potential applications in other domains requiring high-precision text classification. Future work will focus on extending the EIA to other biomedical datasets, optimizing hyperparameters, and deploying the framework in real-time clinical decision-support systems.

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)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation 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 score0.911
Threshold uncertainty score0.842

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0020.005
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 head0.180
GPT teacher head0.362
Teacher spread0.181 · 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.

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

Citations1
Published2024
Admission routes1
Has abstractyes

Explore more

Same venuemedRxivSame topicTopic ModelingFrench-language works237,207