Unsupervised clustering using multiple correspondence analysis reveals clinically-relevant demographic variables across multiple gastrointestinal cancers
Surgical Oncology Insight · 2024
DOI: 10.1016/j.soi.2024.100009 ↗Kurz gefasst
Fachartikel in der Zeitschrift Surgical Oncology Insight, 2024. Verfasst von Ryan J. Kramer und 10 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 21 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
Objective
Patients with gastrointestinal malignancies represent a heterogenous population, even among those with similar stage and treatment pathways. Here, we used dimensionality reduction in the National Cancer Database (NCDB) to inform unsupervised clustering of patients with three gastrointestinal malignancies and examined outcomes among these computationally-derived groups.
Methods
The NCDB was queried for three cohorts of patients receiving multimodal therapy: stage II/III esophageal cancer, stage II/III gastric cancer, and stage III colon cancer. Multiple correspondence analysis (MCA), a dimensionality reduction technique well-suited for categorical variables such as demographic data in the NCDB, was performed on this cohort with variables including demographic and tumor characteristics. Principal components were analyzed to derive clusters. Outcomes for each cluster were compared using Kaplan-Meier survival methods.
Results
For esophageal (n=11,399), gastric (n=2,033), and colon (n=72,057) cancer, the same four variables were identified as highly representative. The principal variables were income quartile, education quartile, age quartile, and insurance type. Survival analysis demonstrated significant differences in overall survival between clusters in esophageal (p
Zitieren
APA
Kramer, R. J., Rhodin, K. E., Therien, A., Raman, V., Eckhoff, A., Thompson, C., Tong, B. C., Blazer, D. G., Lidsky, M. E., D’Amico, T., & Nussbaum, D. P. (2024). Unsupervised clustering using multiple correspondence analysis reveals clinically-relevant demographic variables across multiple gastrointestinal cancers. Surgical Oncology Insight. https://doi.org/10.1016/j.soi.2024.100009
Vancouver
Kramer RJ, Rhodin KE, Therien A, Raman V, Eckhoff A, Thompson C, et al. Unsupervised clustering using multiple correspondence analysis reveals clinically-relevant demographic variables across multiple gastrointestinal cancers. Surgical Oncology Insight. 2024. doi:10.1016/j.soi.2024.100009
BibTeX
@article{Kramer2024,
author = {Kramer, Ryan J. and Rhodin, Kristen E. and Therien, Aaron and Raman, Vignesh and Eckhoff, Austin and Thompson, Camryn and Tong, Betty C. and Blazer, Dan G. and Lidsky, Michael E. and D’Amico, Thomas and Nussbaum, Daniel P.},
title = {Unsupervised clustering using multiple correspondence analysis reveals clinically-relevant demographic variables across multiple gastrointestinal cancers},
journal = {Surgical Oncology Insight},
year = {2024},
doi = {10.1016/j.soi.2024.100009}
}
EUVIMED