# Mapping the ECC–Saliva Neuroimmune Axis Using AI: A System-Level Framework

## TL;DR

This study uses AI to map ECC-saliva research, identifying key themes and underexplored areas like antioxidant and neuroimmune connections for future studies.

## Contribution

A novel AI-assisted framework to map ECC-saliva research, revealing new neuroimmune and redox themes for future investigation.

## Key findings

- Seven thematic clusters were identified, including microbiome, fluoride, and antioxidant/redox themes.
- Antioxidant/redox and peptide-defence markers are emerging but underrepresented compared to classical themes.
- A Candida–cytokine–neuroendocrine triad was identified as a potential testable hypothesis.

## Abstract

What are the main findings?
An AI-assisted bibliometric map of the ECC–saliva literature identifies seven stable thematic clusters spanning microbiome, fluoride, antioxidant/redox, peptide-based immunity, and neuroendocrine salivary research.Emerging ECC–saliva work is increasingly oriented towards antioxidant/redox, proteomic, and peptide-defence markers, which remain comparatively underrepresented relative to classical microbiome and fluoride themes.

An AI-assisted bibliometric map of the ECC–saliva literature identifies seven stable thematic clusters spanning microbiome, fluoride, antioxidant/redox, peptide-based immunity, and neuroendocrine salivary research.

Emerging ECC–saliva work is increasingly oriented towards antioxidant/redox, proteomic, and peptide-defence markers, which remain comparatively underrepresented relative to classical microbiome and fluoride themes.

What are the implications of the main findings?
Treating the ECC–saliva literature as data highlights candidate neuro–immune–redox axes and salivary biomarker panels that can be prioritised in future prospective cohorts and mechanistic studies.The framework supports a more host-centred, systems-oriented approach to paediatric dentistry by linking antioxidant, cytokine, fungal, and neuroendocrine markers into testable, literature-derived hypotheses rather than fixed diagnostic panels.

Treating the ECC–saliva literature as data highlights candidate neuro–immune–redox axes and salivary biomarker panels that can be prioritised in future prospective cohorts and mechanistic studies.

The framework supports a more host-centred, systems-oriented approach to paediatric dentistry by linking antioxidant, cytokine, fungal, and neuroendocrine markers into testable, literature-derived hypotheses rather than fixed diagnostic panels.

Background/Objectives: Early childhood caries (ECC) and saliva have been studied across disparate domains, including microbiome, fluoride, immune, oxidative-stress, and neuroendocrine research. However, the ECC–saliva literature has not previously been mapped as a connected system using modern natural language processing (NLP). This study treats PubMed titles and abstracts as data to identify major themes, emerging topics, and candidate neuroimmune axes in ECC–saliva research. Methods: Using the NCBI E-utilities API, we retrieved 298 PubMed records (2000–2025) matching (“early childhood caries” [Title/Abstract]) AND saliva [Title/Abstract]. Text was cleaned with spaCy and embedded using a transformer encoder; BERTopic combined UMAP dimensionality reduction and HDBSCAN clustering to derive thematic topics. We summarised topics with class-based TF–IDF, constructed keyword co-occurrence networks, defined an internal topic-level Novelty Index (semantic distance plus temporal dispersion), and mapped high-novelty topics to gene ontology and Reactome pathways using g:Profiler. Prophet was used to model temporal trends and forecast topic-level publication trajectories. Finally, we generated a fully synthetic neuroimmune salivary dataset, based on realistic ranges from the literature, to illustrate how the identified axes could be operationalised in future ECC cohorts. Results: Seven coherent ECC–saliva topics were identified, including classical microbiome and fluoride domains as well as antioxidant/redox, proteomic, peptide immunity, and Candida–biofilm themes. High-novelty topics clustered around total antioxidant capacity, glutathione peroxidase, superoxide dismutase, and peptide-based host defence. Keyword networks and ontology enrichment highlighted “Detoxification of Reactive Oxygen Species”, “cellular oxidant detoxification”, and cytokine-mediated signalling as central processes. Temporal forecasting suggested plateauing growth for classical epidemiology and fluoride topics, with steeper projected increases for antioxidant and peptide-immunity themes. A co-mention heatmap revealed a literature-level Candida–cytokine–neuroendocrine triad (e.g., Candida albicans, IL-6/TNF, cortisol), which we propose as a testable neuro-immunometabolic hypothesis rather than a confirmed mechanism. Conclusions: AI-assisted topic modelling and network analysis provide a reproducible, bibliometric map of ECC–saliva research that highlights underexplored antioxidant/redox and neuroimmune salivary axes. The synthetic neuroimmune dataset and modelling pipeline are illustrative only, but together with the literature map, they offer a structured agenda for future ECC cohorts and mechanistic studies.