EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Machine Learning to Predict Implant-Based Breast Reconstruction Failure: A Bootstrap-Validated Elastic Net Model

Machine Learning zur Vorhersage des Versagens der implantatbasierten Brustrekonstruktion: ein bootstrap-validiertes Elastic-Net-Modell

Yanis Berkane, Anna Scarabosio, Glenda G Caputo, Paul Girard, Roberta Albanese, Damiano Tambasco, Nicolas Bertheuil, Frédéric Bodin, Nicolas Jacquinot, Pier Camilo Parodi

Aesthetic Plastic Surgery · 2026-06 · 50 (11) · 4097-4110

DOI: 10.1007/s00266-026-05795-2 ↗

Auf einen Blick

In 381 implantatbasierten Brustrekonstruktionen sagte ein internes Elastic-Net-Modell das Versagen mit guter Trennschärfe vorher. Die AUC betrug 0,856 (95 %-KI 0,76–0,935).

Fragestellung

Kann ein auf präoperativen Variablen basierendes Modell das Versagen der implantatbasierten Brustrekonstruktion vorhersagen?

Methode

Retrospektive Single-Center-Kohortenstudie mit 381 IBR-Eingriffen von 2006 bis 2023; Elastic-Net-Modell; interne Bootstrap-Validierung nach TRIPOD + AI 2024.

Ergebnisse

Die beobachtete Versagensrate betrug 5,5 % (n = 21). Im Endmodell blieben u. a. postoperative Radiotherapie, Expander-Nutzung und die Interaktion zwischen Alter und BMI enthalten.

Einschränkungen

Externe Validierung und Studien zur klinischen Implementierung sind erforderlich.

Schlussfolgerung der Autor:innen

Die Studie beschreibt ein robustes, intern validiertes Vorhersagemodell für Implantatverlust nach IBR. Der Online-Rechner soll in Zukunft eine individuelle Risikoschätzung unterstützen.

Kernaussagen

  • Versagensrate: 5,5 % (n = 21)
  • AUC 0,856 (95 %-KI 0,76–0,935)
  • Online-Rechner für individuelle Risikoschätzung verfügbar

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

Kurz gefasst

Fachartikel in der Zeitschrift Aesthetic Plastic Surgery, online erschienen am 13.04.2026. Verfasst von Yanis Berkane und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Plastic, Reconstructive and Aesthetic Surgery, CHU de Rennes, University of Rennes, 35000, Rennes, France. yanis.berkane@chu-rennes.fr. Hauptthemen laut MEDLINE: Breast Implants, Machine Learning, Breast Implantation, Mammaplasty. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 68 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Centre Hospitalier Universitaire de Rennes.

Auf einen BlickAbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Implant-based reconstruction failure remains a significant complication following breast reconstruction, with substantial implications for patient outcomes. Reliable preoperative risk prediction tools are lacking.

Methods

A retrospective single-center cohort study was conducted, including 381 IBR procedures performed from 2006 to 2023. Reconstruction failure was defined as explantation without immediate replacement within one year. Elastic net regression was used to develop a multivariable model based on age, BMI, smoking status, radiation therapy, chemotherapy, use of expander, and implant plane. Internal bootstrap validation was performed following the 2024 TRIPOD + AI guidelines. Model performance was assessed using AUC, calibration curves, and decision curve analysis. A real-time online calculator was deployed for clinical use.

Results

The mean follow-up was 38.2 ± 27.2 months. The observed IBR failure rate was 5.5% (n = 21). The final model included key predictors such as postoperative radiotherapy, expander use, and an interaction term between age and BMI. Discrimination was strong with an optimism-corrected AUC of 0.856 (95% CI 0.76–0.935). Calibration analysis demonstrated optimal agreement between predicted and observed outcomes, and decision curve analysis confirmed the model’s net clinical benefit over default strategies. The model is accessible via an online tool ( https://urls.fr/BIWCeO ).

Conclusions

This study presents a robust, internally validated predictive model for implant loss following IBR. The online calculator suggests real-time, individualized risk estimation, supporting preoperative counseling and surgical decision-making in the future. External validation and clinical implementation studies are warranted to confirm its broader applicability. Level of Evidence IV This journal requires that authors assign a level of evidence to each article. For a full description of these Evidence-Based Medicine ratings, please refer to the Table of Contents or the online Instructions to Authors www.springer.com/00266.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Breast ImplantsMachine LearningBreast ImplantationMammaplastyBreast NeoplasmsHumansFemaleRetrospective StudiesMiddle AgedAdultRisk AssessmentPredictive Learning ModelsCohort StudiesMastectomyTreatment FailurePrediction Algorithms

Stichwörter der Autor:innen

Breast implantBreast reconstructionImmediate reconstructionMultivariate analysisPredictive scoreRadiationReconstruction failure

Autor:innen und Institutionen

  • Department of Plastic, Reconstructive and Aesthetic Surgery, CHU de Rennes, University of Rennes, 35000, Rennes, France. yanis.berkane@chu-rennes.fr.
  • SITI Laboratory, UMR1236, Etablissement Français du Sang, University of Rennes, 35000, Rennes, France. yanis.berkane@chu-rennes.fr.
  • Plastic and Reconstructive Surgery, Department of Medical Area, University Hospital Santa Maria della Misericordia of Udine, 33100, Udine, Italy.
  • Department of Plastic, Reconstructive and Aesthetic Surgery, CHU de Rennes, University of Rennes, 35000, Rennes, France.
  • SITI Laboratory, UMR1236, Etablissement Français du Sang, University of Rennes, 35000, Rennes, France.
  • Plastic Surgery Unit, San Carlo di Nancy Hospital, 00165, Rome, Italy.

Förderung

  • Centre Hospitalier Universitaire de Rennes

Zitieren

APA

Berkane, Y., Scarabosio, A., Caputo, G. G., Girard, P., Albanese, R., Tambasco, D., Bertheuil, N., Bodin, F., Jacquinot, N., & Parodi, P. C. (2026). Machine Learning to Predict Implant-Based Breast Reconstruction Failure: A Bootstrap-Validated Elastic Net Model. Aesthetic Plastic Surgery, 50(11), 4097-4110. https://doi.org/10.1007/s00266-026-05795-2

Vancouver

Berkane Y, Scarabosio A, Caputo GG, Girard P, Albanese R, Tambasco D, et al. Machine Learning to Predict Implant-Based Breast Reconstruction Failure: A Bootstrap-Validated Elastic Net Model. Aesthetic Plastic Surgery. 2026;50(11):4097-4110. doi:10.1007/s00266-026-05795-2

BibTeX
@article{Berkane2026,
  author = {Berkane, Yanis and Scarabosio, Anna and Caputo, Glenda G and Girard, Paul and Albanese, Roberta and Tambasco, Damiano and Bertheuil, Nicolas and Bodin, Frédéric and Jacquinot, Nicolas and Parodi, Pier Camilo},
  title = {Machine Learning to Predict Implant-Based Breast Reconstruction Failure: A Bootstrap-Validated Elastic Net Model},
  journal = {Aesthetic Plastic Surgery},
  year = {2026},
  volume = {50},
  number = {11},
  pages = {4097--4110},
  doi = {10.1007/s00266-026-05795-2}
}
Kostenlos starten →