AI Risk Prediction Tools for Autologous Breast Reconstruction
Journal of Surgical Oncology · 2026
DOI: 10.1002/jso.70318 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Surgical Oncology, 2026. Verfasst von Jonlin Chen und 10 weiteren Autor:innen. Beteiligte Einrichtung: Plastic and Reconstructive Surgery Service, Department of Surgery, Memorial Sloan Kettering Cancer Center, New York, New York, USA. Hauptthemen laut MEDLINE: Mammaplasty, Postoperative Complications, Breast Neoplasms, Machine Learning. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NCI NIH HHS.
Abstract (Originalsprache)
Background
Autologous breast reconstruction offers patients a durable and natural‐appearing option after mastectomy. However, complication risks include flap loss, infection, and delayed wound healing. This study developed both traditional statistical and machine learning (ML) models to predict the risk of developing a 90‐day postoperative complication after autologous reconstruction.
Methods
Patient data were retrospectively collected for patients who underwent abdominal‐based autologous breast reconstruction at Memorial Sloan Kettering Cancer Center (January 2015‐September 2024). Multivariable logistic regression models and supervised ML models were developed to predict infection, hematoma, seroma, delayed wound healing, and flap compromise.
Results
2,128 patients (3,249 flap reconstructions) were included. Overall, 90‐day complications occurred in 475 (22.3%) patients, including infection (10%), hematoma (6%), delayed healing (4.1%), seroma (3.9%), and flap compromise (2.8%). AUCs ranged from 0.60 to 0.66 (logistic regression) and 0.64 to 0.73 (ML). Higher BMI was associated with increased risk for seroma (OR: 1.1, 95% CI: 1.04–1.13) and neoadjuvant chemotherapy for infection (OR:1.72, 95% CI: 1.17–2.51). Key ML model predictors on SHAP analysis included age, BMI, and pre‐reconstruction radiation.
Conclusion
Individualized risk prediction models for complications after autologous breast reconstruction were developed using traditional statistics and ML. These models may help personalize treatment; however, further research is needed to enhance model predictive performance and clinical utility.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Plastic and Reconstructive Surgery Service, Department of Surgery, Memorial Sloan Kettering Cancer Center, New York, New York, USA.
- Division of Plastic Surgery, Indiana University School of Medicine, Indianapolis, Indiana, USA.
- Department of Epidemiology and Biostatistics, Memorial Sloan Kettering Cancer Center, New York, New York, USA.
ORCID-Profile: Ariel Gabay
Förderung
- NCI NIH HHS
Zitieren
APA
Chen, J., Gabay, A., Hassan, A. M., Graziano, F. D., Boe, L. A., Roberts, A. N., Shammas, R. L., Stern, C. S., Allen, R. J., Mehrara, B. J., & Nelson, J. A. (2026). AI Risk Prediction Tools for Autologous Breast Reconstruction. Journal of Surgical Oncology. https://doi.org/10.1002/jso.70318
Vancouver
Chen J, Gabay A, Hassan AM, Graziano FD, Boe LA, Roberts AN, et al. AI Risk Prediction Tools for Autologous Breast Reconstruction. Journal of Surgical Oncology. 2026. doi:10.1002/jso.70318
BibTeX
@article{Chen2026,
author = {Chen, Jonlin and Gabay, Ariel and Hassan, Abbas M and Graziano, Francis D and Boe, Lillian A and Roberts, Arielle N and Shammas, Ronnie L and Stern, Carrie S and Allen, Robert J and Mehrara, Babak J and Nelson, Jonas A},
title = {AI Risk Prediction Tools for Autologous Breast Reconstruction},
journal = {Journal of Surgical Oncology},
year = {2026},
doi = {10.1002/jso.70318}
}
EUVIMED