EUVIMEDEUVIMED entdecken
Crossref

1148 AI Applications in Pectus Excavatum and Chest Wall Deformities: A Review of Clinical Utility

D Campbell, T Dixitkumar Shah, T Nahar, P Mhandu

British Journal of Surgery · 10.07.2026 · 113 (Supplement_6)

DOI: 10.1093/bjs/znag063.489 ↗

Kurz gefasst

Fachartikel in der Zeitschrift British Journal of Surgery, online erschienen am 10.07.2026. Verfasst von D Campbell und 3 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Aim

Artificial intelligence (AI) is of growing importance in the evaluation and management of chest wall deformities, particularly pectus excavatum (PE). This review aims to clarify the clinical performance, and limitations of AI and machine learning (ML) models to guide its integration into surgical practice.

Method

A systematic search of PubMed, Scopus and Web of Science was conducted from inception to date, identifying English-language, full-text studies applying AI including ML and deep learning (DL) to any clinical stage of chest wall deformity management. Titles and s were screened independently by two reviewers, with a third resolving disagreements. Included studies underwent structured data extraction assessing imaging modality, AI architecture, validation method, performance and degree of automation.

Results

Fourteen studies were included (n=6,214 patients). Eleven studies (73%) used computed tomography, 2 (13%) studies used chest x-rays, and the remaining 2 (13%) used 3D surface scanning. DL was used in 79% of studies, with convolutional neural networks (CNNs), U-Net, and hybrid CNN-Long Short-Term Memory models most common. Reported performance was consistently high, with 90–97% classification accuracy and Dice >0.90 for segmentation. However, no studies employed external validation. Primary clinical applications were diagnosis/severity assessment (50%), anatomical segmentation (36%), and surgical planning or postoperative prediction (29%). Although 71% of models were described as fully automated, 43% still required manual steps.

Conclusions

While AI models show high technical performance in assessing chest wall deformities, clinical readiness remains limited. Enhancing validation, reducing human input, and targeting surgical decision points are necessary to translate these systems into meaningful perioperative tools.

Zitieren

APA

Campbell, D., Shah, T. D., Nahar, T., & Mhandu, P. (2026). 1148 AI Applications in Pectus Excavatum and Chest Wall Deformities: A Review of Clinical Utility. British Journal of Surgery, 113(Supplement_6). https://doi.org/10.1093/bjs/znag063.489

Vancouver

Campbell D, Shah TD, Nahar T, Mhandu P. 1148 AI Applications in Pectus Excavatum and Chest Wall Deformities: A Review of Clinical Utility. British Journal of Surgery. 2026;113(Supplement_6). doi:10.1093/bjs/znag063.489

BibTeX
@article{Campbell2026,
  author = {Campbell, D and Shah, T Dixitkumar and Nahar, T and Mhandu, P},
  title = {1148 AI Applications in Pectus Excavatum and Chest Wall Deformities: A Review of Clinical Utility},
  journal = {British Journal of Surgery},
  year = {2026},
  volume = {113},
  number = {Supplement_6},
  doi = {10.1093/bjs/znag063.489}
}
Kostenlos starten →