Open AccessCLUSTER ANALYSIS IDENTIFIES VARIABLES RELATED TO PROGNOSIS OF BREAST CANCER DISEASE
Author(s) -
Neyva Maria Lopes Romeiro,
Mara Caroline Torres dos SANTOS,
Carolina Panis,
Tiago Viana Flor de Santana,
Paulo Laerte Natti,
Daniel Rech,
Eliandro Rodrigues Cirilo
Publication year - 2021
Publication title -
revista de matemática e estatística
Language(s) - English
Resource type - Journals
eISSN - 1980-4245
pISSN - 0102-0811
DOI - 10.28951/rbb.v39i4.596
Subject(s) - breast cancer , medicine , correlation , oncology , body mass index , spearman's rank correlation coefficient , cluster (spacecraft) , disease , cancer , lymph node , obesity , statistics , mathematics , geometry , computer science , programming language
This work presents a cluster analysis approach aiming to determine distinct groups based on clinicopathological data from patients with breast cancer (BC). For this purpose, the clinical variables were considered: age at diagnosis, weight, height, lymph nodal invasion (LN), tumor-node-metastasis (TNM) staging and body mass index (BMI). Ward's hierarchical clustering algorithm was used to form specific groups. Based on this, BC patients were separated into four groups. The Kruskal-Wallis test was performed to assess the differences among the clusters. The intensity of the influence of variables on the prognosis of BC was also evaluated by calculating the Spearman's correlation. Positive correlations were obtained between weight and BMI, TNM and LN invasion in all analyzes. Negative correlations between BMI and height were obtained in some of the analyzes. Finally, a new correlation was obtained, based on this approach, between weight and TNM, demonstrating that the trophic-adipose status of BC patients can be directly related to disease staging.