EUVIMEDOtkrijte EUVIMED
Open access · CC BY 4.0

Does Patient History Influence Capsular Contracture? An Exploratory Analysis with Machine Learning

Thomas M Johnstone, Daniel Najafali, Jennifer K Shah, Justin M Camacho, Chancellor Johnstone, Rahim S Nazerali, Gordon K Lee

Aesthetic Plastic Surgery · 2026-07 · 50 (13) · 5102-5108

DOI: 10.1007/s00266-026-05919-8 ↗

At a glance

Journal article in Aesthetic Plastic Surgery, published online on 2026-05-29. Written by Thomas M Johnstone and 6 co-authors. Institution: Division of Plastic and Reconstructive Surgery, Stanford University School of Medicine, Stanford, CA, USA. Major MEDLINE topics: Machine Learning, Implant Capsular Contracture, Breast Implantation, Breast Implants. Cited 1 times so far (Crossref); 36 references. The full text is freely available (open access, CC BY 4.0). Funded by: NCATS NIH HHS, National Center for Advancing Translational Sciences.

SažetakSubjectsBibliografski podaciCiteRelated studies

Abstract (original language)

Background

Capsular contracture (CC) is a frequent and distressing complication of breast augmentation and reconstruction. Although numerous patient-, surgical-, and implant-related risk factors have been proposed, reliable population-level predictors remain inconsistent across studies. This study evaluates whether administrative medical history, as encoded by ICD and CPT codes, contains sufficient predictive signal to identify patients at risk for CC using machine learning.

Methods

Patients were queried from the Merative TM MarketScan® Research Databases from 2003 to 2017 with CPT codes for implant-based breast reconstruction and augmentation. ICD codes were then used to identify all events and conditions of a patient’s history. Hyperparameter-tuned random forest models were combined with multivariable logistic regression models to validate risk factors for the development of CC.

Results

A total of 112,489 patients were included, and the rate of capsular contracture was 9.55%. In total, 4,825 common conditions and procedures were included as features in the model. The random forest’s error rate was 9.54%. Prior CC was the most important variable in the model. When removed, model accuracy decreased by 0.0011% ( p

Subjects

MeSH terms (MEDLINE)

Machine LearningImplant Capsular ContractureBreast ImplantationBreast ImplantsMammaplastyHumansFemaleAdultMiddle AgedRandom ForestRisk FactorsRisk AssessmentRetrospective StudiesPredictive Learning ModelsDatabases, FactualLogistic ModelsPrediction Algorithms

Author keywords

Alloplastic reconstructionArtificial intelligenceBreastBreast implantsBreast reconstructionCapsular contractureComplicationsContracture formationImplantImplant capsular contractureImplant-based reconstructionMachine learningMammaplastyOutcomes predictionPostoperative complications

Authors and institutions

  • Division of Plastic and Reconstructive Surgery, Stanford University School of Medicine, Stanford, CA, USA.
  • Carle Illinois College of Medicine, University of Illinois Urbana-Champaign, Urbana, IL, USA. danieln6@illinois.edu.
  • Drexel University College of Medicine, Philadelphia, PA, USA.
  • Air Force Institute of Technology, Wright-Patterson AFB, Dayton, OH, USA.
  • Division of Plastic and Reconstructive Surgery, Stanford University School of Medicine, Stanford, CA, USA. gordokl1@hs.uci.edu.
  • Department of Plastic Surgery, University of California, Irvine, Orange, CA, USA. gordokl1@hs.uci.edu.

Funding

  • NCATS NIH HHS
  • National Center for Advancing Translational Sciences

Cite

APA

Johnstone, T. M., Najafali, D., Shah, J. K., Camacho, J. M., Johnstone, C., Nazerali, R. S., & Lee, G. K. (2026). Does Patient History Influence Capsular Contracture? An Exploratory Analysis with Machine Learning. Aesthetic Plastic Surgery, 50(13), 5102-5108. https://doi.org/10.1007/s00266-026-05919-8

Vancouver

Johnstone TM, Najafali D, Shah JK, Camacho JM, Johnstone C, Nazerali RS, et al. Does Patient History Influence Capsular Contracture? An Exploratory Analysis with Machine Learning. Aesthetic Plastic Surgery. 2026;50(13):5102-5108. doi:10.1007/s00266-026-05919-8

BibTeX
@article{Johnstone2026,
  author = {Johnstone, Thomas M and Najafali, Daniel and Shah, Jennifer K and Camacho, Justin M and Johnstone, Chancellor and Nazerali, Rahim S and Lee, Gordon K},
  title = {Does Patient History Influence Capsular Contracture? An Exploratory Analysis with Machine Learning},
  journal = {Aesthetic Plastic Surgery},
  year = {2026},
  volume = {50},
  number = {13},
  pages = {5102--5108},
  doi = {10.1007/s00266-026-05919-8}
}
Start for free →