EUVIMEDEUVIMED entdecken
ValidierungsstudieOpen Access · CC BY-NC-ND 4.0

Large language models for early childhood caries risk triage: A validation study using standardized pediatric dental vignettes

Balaji Suresh, Nandini Devi Madiajagane, Maria Anthonet Sruthi

Journal of Indian Society of Pedodontics and Preventive Dentistry · 2026-07 · 44 (4) · 392-398

DOI: 10.4103/jisppd.jisppd_203_26 ↗

Kurz gefasst

Validierungsstudie in der Zeitschrift Journal of Indian Society of Pedodontics and Preventive Dentistry, online erschienen am 25.08.2026. Verfasst von Balaji Suresh und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Pediatric and Preventive Dentistry, SRM Dental College, Chennai, Tamil Nadu, India. Hauptthemen laut MEDLINE: Dental Caries, Triage. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

To compare the diagnostic accuracy and public health utility of Gemini 2.5 Flash and GPT-4 for early childhood caries (ECC) risk triage in classifying presentations as high risk (warranting immediate referral) or low risk (amenable to preventive counseling). Materials and Methods: A standardized dataset of 50 clinical vignettes (25 high risk and 25 low risk) was evaluated against both large language models via official application programming interfaces using a blinded, prospective comparative design (CONSORT-AI; TRIPOD+AI). This constitutes a vignette-based internal validation study and does not represent a clinical diagnostic accuracy study. Ground truth was established by two consultant pediatric dentists (intraclass correlation coefficient = 0.92). Performance was quantified using sensitivity, specificity, positive predictive value, negative predictive value, and false negative rate (FNR). Readability, actionability, and multilingual competence in Hindi and Tamil were additionally assessed.

Results

Both models exceeded the 80% accuracy threshold. GPT-4 achieved significantly higher sensitivity (92.0% vs. 80.0%; P = 0.032) and a lower FNR (8.0% vs. 20.0%), with superior readability (Flesch-Kincaid Grade Level 5.9 vs. 8.1), actionability (4.8 vs. 4.2), and cross-lingual consistency. Both models achieved 100% safety disclaimer compliance in English.

Conclusions

GPT-4 demonstrates a statistically superior safety profile for ECC risk triage. As a Level 1 adjunct, it can assist pediatric dentists by prescreening caregiver-reported presentations, reducing diagnosis lag, and directing specialist capacity toward confirmed high-risk pathology without replacing clinical judgment. Clinical Relevance: This study establishes that GPT-4 is a safer and more accessible AI triage tool than Gemini 2.5 Flash for pediatric dental screening, particularly in linguistically diverse, resource-constrained settings where specialist access is limited.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Dental CariesTriageHumansLarge Language ModelsChild, PreschoolProspective StudiesRisk AssessmentPediatric DentistrySensitivity and Specificity

Stichwörter der Autor:innen

Artificial intelligenceGPT-4Gemini 2.5 flashdiagnostic accuracyearly childhood carieslarge language modelspediatric dentistrysensitivitytriage

Autor:innen und Institutionen

  • Department of Pediatric and Preventive Dentistry, SRM Dental College, Chennai, Tamil Nadu, India.
  • Department of Dentistry, Maa Kauvery Women and Children's Hospital, Tiruchirappalli, Tamil Nadu, India.
  • Department of Pedodontics and Preventive Dentistry, Saveetha Dental College and Hospitals, Saveetha Institute of Medical and Technical Sciences, Saveetha University, Chennai, Tamil Nadu, India.

Zitieren

APA

Suresh, B., Madiajagane, N. D., & Sruthi, M. A. (2026). Large language models for early childhood caries risk triage: A validation study using standardized pediatric dental vignettes. Journal of Indian Society of Pedodontics and Preventive Dentistry, 44(4), 392-398. https://doi.org/10.4103/jisppd.jisppd_203_26

Vancouver

Suresh B, Madiajagane ND, Sruthi MA. Large language models for early childhood caries risk triage: A validation study using standardized pediatric dental vignettes. Journal of Indian Society of Pedodontics and Preventive Dentistry. 2026;44(4):392-398. doi:10.4103/jisppd.jisppd_203_26

BibTeX
@article{Suresh2026,
  author = {Suresh, Balaji and Madiajagane, Nandini Devi and Sruthi, Maria Anthonet},
  title = {Large language models for early childhood caries risk triage: A validation study using standardized pediatric dental vignettes},
  journal = {Journal of Indian Society of Pedodontics and Preventive Dentistry},
  year = {2026},
  volume = {44},
  number = {4},
  pages = {392--398},
  doi = {10.4103/jisppd.jisppd_203_26}
}
Kostenlos starten →