EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Clinical Reliability of AI-Based Cephalometric Analysis Using WebCeph: A Comparative Agreement Study

Ali Azari-Mehr iD, Angela Bisbal-Puchades, Laura Marqués-Martínez iD, Maria Carmona-Santamaria, Esther García-Miralles iD, Juan Ignacio Aura-Tormos iD, Clara Guinot-Barona iD

Journal of Clinical Medicine · 28.05.2026 · 15 (11) · 4155

DOI: 10.3390/jcm15114155 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Clinical Medicine, online erschienen am 28.05.2026. Verfasst von Ali Azari-Mehr und 6 weiteren Autor:innen. Beteiligte Einrichtung: Dentistry Department, Medicine and Health Science Faculty, Catholic University of Valencia, 46001 Valencia, Spain. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background/Objectives: Artificial intelligence has accelerated cephalometric analysis by enabling rapid and standardized measurements. However, whether these automated outputs can be considered clinically interchangeable with expert manual tracing remains unresolved, particularly for routinely used analyses such as Steiner.

Methods

A comparative experimental study was conducted on 100 lateral cephalometric radiographs analysed using two parallel approaches: expert manual tracing and fully automated analysis with the WebCeph platform. Seven Steiner variables (SNA, SNB, ANB, 1–NA, 1–NB, interincisal angle, and FMA) were evaluated. Paired t-tests were used to assess differences between methods, while agreement was evaluated using intraclass correlation coefficients and Bland–Altman analysis. Particularly low agreement was observed for clinically relevant parameters such as ANB and FMA.

Results

Six of the seven variables showed statistically significant differences between methods. Automated measurements systematically tended to overestimate both skeletal and dental parameters. Agreement was inconsistent and frequently poor, with ICC values ranging from 0.01 to 0.60 for clinically relevant variables such as ANB and FMA. Importantly, small or non-significant mean differences did not translate into acceptable agreement. Bland–Altman analysis confirmed the presence of systematic bias and wide limits of agreement, especially for dental measurements.

Conclusions

Despite its speed and automation, WebCeph does not achieve clinically acceptable agreement with expert manual tracing across several key cephalometric variables. The observed discrepancies—particularly in parameters critical for sagittal and vertical diagnosis—may compromise clinical interpretation and treatment planning. These findings support the use of AI-based cephalometric analysis as an adjunctive tool rather than a substitute for clinician-guided evaluation.

Schlagwörter

Stichwörter der Autor:innen

artificial intelligencecephalometrydiagnostic imagingorthodonticsreproducibility of results

Autor:innen und Institutionen

  • Dentistry Department, Medicine and Health Science Faculty, Catholic University of Valencia, 46001 Valencia, Spain.
  • Stomatology Department, University of Valencia, 46010 Valencia, Spain.

ORCID-Profile: Ali Azari-Mehr, Laura Marqués-Martínez, Esther García-Miralles, Juan Ignacio Aura-Tormos, Clara Guinot-Barona

Zitieren

APA

Azari-Mehr, A., Bisbal-Puchades, A., Marqués-Martínez, L., Carmona-Santamaria, M., García-Miralles, E., Aura-Tormos, J. I., & Guinot-Barona, C. (2026). Clinical Reliability of AI-Based Cephalometric Analysis Using WebCeph: A Comparative Agreement Study. Journal of Clinical Medicine, 15(11), 4155. https://doi.org/10.3390/jcm15114155

Vancouver

Azari-Mehr A, Bisbal-Puchades A, Marqués-Martínez L, Carmona-Santamaria M, García-Miralles E, Aura-Tormos JI, et al. Clinical Reliability of AI-Based Cephalometric Analysis Using WebCeph: A Comparative Agreement Study. Journal of Clinical Medicine. 2026;15(11):4155. doi:10.3390/jcm15114155

BibTeX
@article{AzariMehr2026,
  author = {Azari-Mehr, Ali and Bisbal-Puchades, Angela and Marqués-Martínez, Laura and Carmona-Santamaria, Maria and García-Miralles, Esther and Aura-Tormos, Juan Ignacio and Guinot-Barona, Clara},
  title = {Clinical Reliability of AI-Based Cephalometric Analysis Using WebCeph: A Comparative Agreement Study},
  journal = {Journal of Clinical Medicine},
  year = {2026},
  volume = {15},
  number = {11},
  pages = {4155},
  doi = {10.3390/jcm15114155}
}
Kostenlos starten →