MétaCan
Menu
Back to cohort
Record W7116899545 · doi:10.1109/jbhi.2025.3647413

DePerio: Innovative Deep Learning-based Framework for Periodontal Disease Diagnosis and Severity Evaluation Using Saliva Samples

2025· article· en· W7116899545 on OpenAlexaff
Mahdi Amrollahi Biouki, Fatemeh Soheili, Niloufar Delfan, Negin Masoudifar, Navid Mohaghegh, Shahin Ebrahimi, S. M. Mahdi H. Daneshvar, Yasaman Tahernezhad, Chunxiang Sun, M Glogauer, Ebrahim Ghafar‐Zadeh

Bibliographic record

VenueIEEE Journal of Biomedical and Health Informatics · 2025
Typearticle
Languageen
FieldDentistry
TopicOral microbiology and periodontitis research
Canadian institutionsUniversity Health NetworkUniversity of TorontoYork University
Fundersnot available
KeywordsSalivaPeriodontitisAggregatibacter actinomycetemcomitansPeriodontal diseaseDeep learningDisease

Abstract

fetched live from OpenAlex

Recent research has identified salivary oral polymorphonuclear neutrophils (oPMNs) as reliable cellular biomarkers for monitoring the progression of periodontal disease (PD). While conventional diagnostic tools such as periodontal probing and radiographic imaging are effective at detecting advanced disease stages, they lack the sensitivity required for early diagnosis. oPMNs, derived from circulating white blood cells (WBCs), transmigrate through the oral epithelium and appear in saliva with diverse morphological characteristics. Although deep learning-based WBC quantification has been extensively explored using peripheral blood datasets, the unique morphology of oPMNs necessitates the development of new image datasets and retraining of models tailored to their detection. To address these challenges, we introduce DePerio-an AI-powered diagnostic pipeline that integrates a novel oPMN isolation protocol with deep neural network (DNN) architectures. We evaluate the performance of multiple DNN models to achieve accurate detection and quantification of oPMNs. Validated against standard quantification methods for oPMNs and oral inflammatory load (OIL), DePerio achieved a detection error rate of less than 5%. In a clinical study involving 111 human saliva samples, spanning individuals from healthy to severe periodontitis cases, and successfully classified five distinct OIL levels. This robust and low-complexity platform provides a scalable and practical solution for early PD detection and longitudinal monitoring in clinical dental practice.

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)0.002
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: Observational
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.324
Threshold uncertainty score0.400

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0020.001
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 science0.0000.000
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 head0.087
GPT teacher head0.426
Teacher spread0.339 · 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 designObservational
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

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueIEEE Journal of Biomedical and Health InformaticsSame topicOral microbiology and periodontitis researchFrench-language works237,207