MétaCan
Menu
Back to cohort
Record W4411477178 · doi:10.1101/2025.06.18.25329494

Artificial Intelligence for Pre-Anaemic Iron Deficiency Detection Using Rich Complete Blood Count Data

2025· preprint· en· W4411477178 on OpenAlexaff
D. Kreuter, Simon Deltadahl, Martin Besser, John R. Bradley, Julian Gilbey, Stephen Kaptoge, Nathalie Kingston, Willem H. Ouwehand, David E. Roberts, Olga Shamardina, Kathleen Stirrups, Dorine W. Swinkels, Dragana Vuckovic, James H.F. Rudd, Emanuele Di Angelantonio, Carola‐Bibiane Schönlieb, Parashkev Nachev, Suthesh Sivapalaratnam, Nicholas Gleadall, Michael Roberts

Bibliographic record

VenuemedRxiv · 2025
Typepreprint
Languageen
FieldMedicine
TopicErythropoietin and Anemia Treatment
Canadian institutionsNutrasource
FundersNIHR Cambridge Biomedical Research CentreEconomic and Social Research CouncilUniversity of CambridgeNIHR BioResourceChief Scientist Office, Scottish Government Health and Social Care DirectorateMedical Research CouncilPublic Health AgencyDepartment of Health and Social CareScottish GovernmentBritish Heart FoundationEngineering and Physical Sciences Research CouncilHealth and Social Care Research and Development DivisionNational Institute for Health and Care ResearchNHS Blood and Transplant
KeywordsComplete blood countAnalyserIron deficiencyCount dataBlood countMedicineAnemiaPediatricsInternal medicineStatisticsMathematics

Abstract

fetched live from OpenAlex

Abstract Iron deficiency (ID) is a major contributor to global disease burden and the leading cause of anaemia. Early detection is important for proactive management, but conventional complete blood count (CBC) screening often fails to identify non-anaemic iron deficiency (NAID) as many individuals maintain haemoglobin and red cell indices within reference ranges. Analysing 153,565 subjects from the INTERVAL, COMPARE and STRIDES studies, we show that CBC screening has only 40.5 % sensitivity for ID detection, falling to 21.9 % for NAID, highlighting a detection gap. CBC analysers generate a wealth of data beyond Electronic Health Record CBC parameters. We demonstrate that artificial intelligence applied to single-cell flow cytometry data from the CBC analyser achieves 83.7 % sensitivity for ID and 79.3 % for NAID. Our findings show that AI can greatly improve detection of a high-prevalence, important condition without changing infrastructure or diagnostic pathways, providing a valuable tool for proactive anaemia management.

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)0.003
metaresearch head score (Gemma)0.013
Version: metacan-v3-hybrid-931329e0061cValidation 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: Empirical
Teacher disagreement score0.003
Threshold uncertainty score0.016

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0030.013
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0020.001
Science and technology studies0.0000.000
Scholarly communication0.0020.001
Open science0.0000.001
Research integrity0.0010.001
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 head0.134
GPT teacher head0.374
Teacher spread0.240 · 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 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

Citations2
Published2025
Admission routes1
Has abstractyes

Explore more

Same venuemedRxivSame topicErythropoietin and Anemia TreatmentFrench-language works237,207