Extremity Soft Tissue Sarcoma Reconstruction Nomograms: A Clinicoradiomic, Machine Learning–Powered Predictor of Postoperative Outcomes
JCO Clinical Cancer Informatics · 2025
DOI: 10.1200/cci-25-00007 ↗Kurz gefasst
Fachartikel in der Zeitschrift JCO Clinical Cancer Informatics, 2025. Verfasst von Rami Elmorsi und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Plastic Surgery, The University of Texas MD Anderson Cancer Center, Houston, TX. Hauptthemen laut MEDLINE: Nomograms, Sarcoma, Machine Learning, Postoperative Complications. Die Arbeit nennt 39 Literaturangaben.
Abstract (Originalsprache)
PURPOSE The choice of wound closure modality after limb-sparing extremity soft-tissue sarcoma (eSTS) resection is fraught with uncertainty. Leveraging machine learning and clinicoradiomic data, we developed Sarcoma Reconstruction Nomograms (SARCON), a tool that provides probabilistic estimates of five adverse outcomes on the basis of the selected reconstructive modality. METHODS This retrospective cohort study of limb-sparing eSTS resections integrated clinical variables and radiomic features, including eSTS and limb dimensions. Target outcomes included surgical site infections (SSI), wound dehiscence (WD), seroma formation, and minor and major complications. For each outcome, three machine learning classifiers—Logistic Regression with Lasso regularization, Naïve Bayes, and FasterRisk—were developed and evaluated using 10-fold cross-validation (CV), 50 random 80%-20% splits, leave-one-out CV, and a test data set. The best-performing model for each outcome was used to construct a respective nomogram. RESULTS A total of 316 limb-sparing eSTS resections were analyzed, predominantly located in the thigh (54%), lower leg (17%), and upper arm (11%). Postoperative outcomes included SSI (12%), WD (16%), seroma formation (8.5%), minor complications (34%), and major complications (25%). Logistic Regression with Lasso regularization consistently outperformed the other models across all outcomes, achieving area under the receiver operator curves ranging from 0.83 to 0.93 in all tests. CONCLUSION By providing probabilistic estimates of adverse outcomes on the basis of reconstructive modality, SARCON empowers surgeons to anticipate complications and optimize reconstructive strategies
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Plastic Surgery, The University of Texas MD Anderson Cancer Center, Houston, TX.
- Department of Plastic, Reconstructive, and Hand Surgery, University Medical Center Utrecht, Utrecht, the Netherlands.
- Department of Surgical Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX.
- Department of Orthopedic Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX.
ORCID-Profile: Rami Elmorsi, Luis D Camacho, David D Krijgh, Heather Lyu, Keila Torres, Valerae Lewis, Christina L Roland, Alexander F Mericli
Zitieren
APA
Elmorsi, R., Camacho, L. D., Krijgh, D. D., Lyu, H., Roubaud, M. S., Torres, K., Lewis, V., Roland, C. L., & Mericli, A. F. (2025). Extremity Soft Tissue Sarcoma Reconstruction Nomograms: A Clinicoradiomic, Machine Learning–Powered Predictor of Postoperative Outcomes. JCO Clinical Cancer Informatics. https://doi.org/10.1200/cci-25-00007
Vancouver
Elmorsi R, Camacho LD, Krijgh DD, Lyu H, Roubaud MS, Torres K, et al. Extremity Soft Tissue Sarcoma Reconstruction Nomograms: A Clinicoradiomic, Machine Learning–Powered Predictor of Postoperative Outcomes. JCO Clinical Cancer Informatics. 2025. doi:10.1200/cci-25-00007
BibTeX
@article{Elmorsi2025,
author = {Elmorsi, Rami and Camacho, Luis D and Krijgh, David D and Lyu, Heather and Roubaud, Margaret S and Torres, Keila and Lewis, Valerae and Roland, Christina L and Mericli, Alexander F},
title = {Extremity Soft Tissue Sarcoma Reconstruction Nomograms: A Clinicoradiomic, Machine Learning–Powered Predictor of Postoperative Outcomes},
journal = {JCO Clinical Cancer Informatics},
year = {2025},
doi = {10.1200/cci-25-00007}
}
EUVIMED