MétaCan
Menu
Back to cohort
Record W3108384885 · doi:10.21203/rs.3.rs-40780/v1

Decoding semi-automated title-abstract screening: a retrospective exploration of the review, study, and publication characteristics associated with accurate relevance predictions

2020· preprint· en· W3108384885 on OpenAlexafffund
Allison Gates, Michelle Gates, Daniel DaRosa, Sarah A. Elliott, Jennifer Pillay, Sholeh Rahman, Ben Vandermeer, Lisa Hartling

Bibliographic record

VenueResearch Square · 2020
Typepreprint
Languageen
FieldBiochemistry, Genetics and Molecular Biology
TopicBiomedical Text Mining and Ontologies
Canadian institutionsUniversity of Alberta
FundersGovernment of CanadaAgency for Healthcare Research and QualityU.S. Department of Health and Human Services
KeywordsRelevance (law)Decoding methodsComputer scienceInformation retrievalData scienceData miningAlgorithmPolitical science

Abstract

fetched live from OpenAlex

Abstract Background We evaluated the benefits and risks of using the Abstrackr machine learning (ML) tool to semi-automate title-abstract screening, and explored whether Abstrackr’s predictions varied by review or study-level characteristics. Methods For 16 reviews we screened a 200-record training set in Abstrackr and downloaded the predicted relevance of the remaining records. We retrospectively simulated the liberal-accelerated screening approach: one reviewer screened the records predicted as relevant; a second reviewer screened those predicted as irrelevant and those excluded by the first reviewer. We estimated the time savings and proportion missed compared with dual independent screening. For reviews with pairwise meta-analyses, we evaluated changes to the pooled effects after removing the missed studies. We explored whether the tool’s predictions varied by review and study-level characteristics using Fisher’s Exact and unpaired t-tests. Results Using the ML-assisted liberal-accelerated approach, we wrongly excluded 0 to 3 (0 to 14%) records but saved a median (IQR) 26 (33) hours of screening time. Removing missed studies from meta-analyses did not alter the reviews’ conclusions. Of 802 records in the final reports, 87% were correctly predicted as relevant. The correctness of the predictions did not differ by review (systematic or rapid, P=0.37) or intervention type (simple or complex, P=0.47). The predictions were more often correct in reviews with multiple (89%) vs. single (83%) research questions (P=0.01), or that included only trials (95%) vs. multiple designs (86%) (P=0.003). At the study level, trials (91%), mixed methods (100%), and qualitative (93%) studies were more often correctly predicted as relevant compared with observational studies (79%) or reviews (83%) (P=0.0006). Studies at high or unclear (88%) vs. low risk of bias (80%) (P=0.039), and those published more recently (mean (SD) 2008 (7) vs. 2006 (10), P=0.02) were more often correctly predicted as relevant. Conclusion Our screening approach saved time and may be suitable in conditions where the limited risk of missing relevant records is acceptable. ML-assisted screening may be most trustworthy for reviews that seek to include only trials. Several of our findings are paradoxical, and require further study to fully understand the tasks to which ML-assisted screening is best suited.

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)0.267
metaresearch head score (Gemma)0.695
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch
Consensus categoriesMetaresearch
DomainCandidate signal: Methods · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: Observational
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.733
Threshold uncertainty score0.904

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.2670.695
Meta-epidemiology (narrow)0.0020.001
Meta-epidemiology (broad)0.0030.007
Bibliometrics0.0090.009
Science and technology studies0.0010.001
Scholarly communication0.0040.004
Open science0.0020.003
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0030.001

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 head0.107
GPT teacher head0.399
Teacher spread0.291 · 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; the direct Gemma label and the distilled Codex classifier agree on what is shown here.

Study designObservational
DomainMethods
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
Published2020
Admission routes2
Has abstractyes

Explore more

Same venueResearch SquareSame topicBiomedical Text Mining and OntologiesFrench-language works237,207