EUVIMEDEUVIMED entdecken
ÜbersichtsarbeitMetaanalyseOpen Access · CC BY-NC-SA 4.0

Diagnostic Accuracy of Artificial Intelligence in Detecting Oral Potentially Malignant Disorders and Oral Cancer: A Meta-Analysis of Imaging-Based Studies (2015–2024)

Diagnostische Genauigkeit von künstlicher Intelligenz beim Erkennen oraler potenziell maligner Störungen und von Mundkrebs: Metaanalyse bildgebender Studien (2015–2024)

M Nayana, J Avinash, M Y Jayachandra, Padma K Bhat, Subodh Kumar, Lipsa Bhuyan

Journal of International Society of Preventive and Community Dentistry · 2025-09 · 15 (5) · 391-401

DOI: 10.4103/jispcd.jispcd_116_25 ↗

Auf einen Blick

35 Studien zeigten eine hohe diagnostische Genauigkeit KI-gestützter Bildverfahren für OPMDs und Mundkrebs. Die gepoolte Sensitivität lag bei 0,919 und die Spezifität bei 0,879.

Fragestellung

Wie genau erkennen KI-gestützte bildbasierte Verfahren OPMDs und Mundkrebs in community- und klinischen Settings?

Methode

Metaanalyse random-effects; Suche in PubMed, IEEE Xplore, Scopus und Web of Science (2015–2024); Qualitätsbewertung mit QUADAS-2.

Ergebnisse

35 Studien mit >15.000 Bildern. Gepoolte Sensitivität 0,919 (95 %-KI 0,89–0,94), Spezifität 0,879 (95 %-KI 0,84–0,91), AUC 0,9758, diagnostische Odds Ratio 131,63.

Schlussfolgerung der Autor:innen

KI-gestützte Diagnosesysteme zeigen eine hohe Genauigkeit und Potenzial für skalierbares, nichtinvasives Screening von OPMDs und Mundkrebs.

Kernaussagen

  • Gepoolte Sensitivität 0,919
  • Gepoolte Spezifität 0,879
  • Deep-Learning-Methoden, besonders CNNs, schnitten am besten ab

Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Journal of International Society of Preventive and Community Dentistry, online erschienen am 04.10.2025. Verfasst von M Nayana und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Public Health Dentistry, Dayananda Sagar College of Dental Sciences, Bengaluru, Karnataka, India. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-SA 4.0).

Auf einen BlickAbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

A bstract Aim: Oral cancer is a leading cause of cancer-related morbidity, especially in low-resource settings. Early detection of oral potentially malignant disorders (OPMDs) is key to reducing disease burden. This study was carried out to evaluate the diagnostic accuracy of AI-assisted imaging tools in the detection of OPMDs and oral cancer in community and clinical settings. Materials and Methods: We searched PubMed, IEEE Xplore, Scopus, and Web of Science (2015–2024) for studies using AI to detect OPMDs or oral cancer from images, reporting sensitivity and specificity. A random-effects meta-analysis was conducted. Quality was assessed using QUADAS-2. Summary receiver operating characteristic curves were generated to evaluate the global performance.

Results

From 1092 articles screened, 35 studies met inclusion criteria. These studies evaluated >15,000 images using clinical photography, histopathology, optical coherence tomography, and autofluorescence. Pooled sensitivity was 0.919% (95% CI: 0.89–0.94), specificity 0.879 (95% CI: 0.84–0.91), area under curve 0.9758, and diagnostic odds ratio 131.63. Deep learning methods—particularly convolutional neural networks—consistently demonstrated superior performance.

Conclusion

AI-assisted diagnostic systems demonstrate high accuracy and potential for scalable, non-invasive screening of OPMDs and oral cancer. Integration into public health programs, particularly in underserved settings, could significantly improve early detection outcomes. Mobile-compatible platforms represent a viable public health tool for oral cancer control.

Schlagwörter

Stichwörter der Autor:innen

Artificial intelligenceCommunity DentistryDeep Learningiagnostic accuracymeta-analysisoral canceroral potentially malignant disorders

Autor:innen und Institutionen

  • Department of Public Health Dentistry, Dayananda Sagar College of Dental Sciences, Bengaluru, Karnataka, India.
  • Department of Public Health Dentistry, Rajarajeswari Dental College and Hospital, Bengaluru, Karnataka, India.
  • Department of Public Health Dentistry, UCMS College of Dental Surgery, Bhairahawa, Nepal.
  • Department of Oral and Maxillofacial Pathology, Kalinga Institute of Dental Sciences, Patia, Bhubaneshwar, Odisha, India.

Zitieren

APA

Nayana, M., Avinash, J., Jayachandra, M. Y., Bhat, P. K., Kumar, S., & Bhuyan, L. (2025). Diagnostic Accuracy of Artificial Intelligence in Detecting Oral Potentially Malignant Disorders and Oral Cancer: A Meta-Analysis of Imaging-Based Studies (2015–2024). Journal of International Society of Preventive and Community Dentistry, 15(5), 391-401. https://doi.org/10.4103/jispcd.jispcd_116_25

Vancouver

Nayana M, Avinash J, Jayachandra MY, Bhat PK, Kumar S, Bhuyan L. Diagnostic Accuracy of Artificial Intelligence in Detecting Oral Potentially Malignant Disorders and Oral Cancer: A Meta-Analysis of Imaging-Based Studies (2015–2024). Journal of International Society of Preventive and Community Dentistry. 2025;15(5):391-401. doi:10.4103/jispcd.jispcd_116_25

BibTeX
@article{Nayana2025,
  author = {Nayana, M and Avinash, J and Jayachandra, M Y and Bhat, Padma K and Kumar, Subodh and Bhuyan, Lipsa},
  title = {Diagnostic Accuracy of Artificial Intelligence in Detecting Oral Potentially Malignant Disorders and Oral Cancer: A Meta-Analysis of Imaging-Based Studies (2015–2024)},
  journal = {Journal of International Society of Preventive and Community Dentistry},
  year = {2025},
  volume = {15},
  number = {5},
  pages = {391--401},
  doi = {10.4103/jispcd.jispcd_116_25}
}
Kostenlos starten →