EUVIMEDEUVIMED entdecken
Crossref

The Impact of AI on Eye Gaze Patterns in Chest X-Ray Interpretation. An Eye Tracking Study of Novice and Expert Radiologists

Dana Belde, Armand Kapaj, Sara Irina Fabrikant, Tumasch Reichenbacher, Thomas Frauenfelder, Thi Dan Linh Nguyen-Kim, André Euler, Mattias Kettner, Michael Josef Thali, R. Huch, Tilo Niemann

Zurich Open Repository and Archive (University of Zurich) · 13.04.2026

DOI: 10.5167/uzh-433650 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Zurich Open Repository and Archive (University of Zurich), erschienen am 13.04.2026. Verfasst von Dana Belde und 10 weiteren Autor:innen.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

To investigate how artificial intelligence–assisted chest radiograph interpretation influences eye gaze patterns in novice and expert radiologists. Materials and Methods: This prospective eye tracking study included 6 novice radiology residents and 6 expert cardiothoracic radiologists. Fifty anonymized posteroanterior chest radiographs were interpreted under 3 conditions: Before AI , With AI , and After AI . An AI-Rad Companion Chest x-ray algorithm generated visual annotations and confidence scores. Eye movements were recorded at 250 Hz. Fixation sequences were analyzed using a 7 × 7 grid and quantified with normalized Levenshtein distance as a measure of systematic viewing behavior. Linear mixed-effects models assessed the effects of condition, expertise, and their interaction.

Results

Viewing patterns were significantly less systematic in the With AI and After AI conditions compared with Before AI. A significant interaction between condition and expertise was observed. Novice radiologists demonstrated markedly increased gaze dissimilarity during AI-assisted interpretation and remained less systematic after AI exposure. Expert radiologists showed no significant differences in gaze behavior across conditions, maintaining stable and systematic viewing patterns.

Conclusions

AI assistance disrupted systematic visual search behavior in novice radiologists but not in experts. These findings indicate that AI exposure may interfere with the stability of foundational perceptual search strategies in trainees, whereas experts integrate AI without altering established viewing patterns. Implications for radiology training warrant careful consideration.

Schlagwörter

AI-assisted diagnosischest X-ray interpretationgaze patternsvisual search behaviorradiologist expertiseradiology educationfixation sequencesLevenshtein distance

Zitieren

APA

Belde, D., Kapaj, A., Fabrikant, S. I., Reichenbacher, T., Frauenfelder, T., Nguyen-Kim, T. D. L., Euler, A., Kettner, M., Thali, M. J., Huch, R., & Niemann, T. (2026). The Impact of AI on Eye Gaze Patterns in Chest X-Ray Interpretation. An Eye Tracking Study of Novice and Expert Radiologists. Zurich Open Repository and Archive (University of Zurich). https://doi.org/10.5167/uzh-433650

Vancouver

Belde D, Kapaj A, Fabrikant SI, Reichenbacher T, Frauenfelder T, Nguyen-Kim TDL, et al. The Impact of AI on Eye Gaze Patterns in Chest X-Ray Interpretation. An Eye Tracking Study of Novice and Expert Radiologists. Zurich Open Repository and Archive (University of Zurich). 2026. doi:10.5167/uzh-433650

BibTeX
@article{Belde2026,
  author = {Belde, Dana and Kapaj, Armand and Fabrikant, Sara Irina and Reichenbacher, Tumasch and Frauenfelder, Thomas and Nguyen-Kim, Thi Dan Linh and Euler, André and Kettner, Mattias and Thali, Michael Josef and Huch, R. and Niemann, Tilo},
  title = {The Impact of AI on Eye Gaze Patterns in Chest X-Ray Interpretation. An Eye Tracking Study of Novice and Expert Radiologists},
  journal = {Zurich Open Repository and Archive (University of Zurich)},
  year = {2026},
  doi = {10.5167/uzh-433650}
}
Kostenlos starten →