Applied Medical Informatics (Sep 2024)
Exploring the Significance of Cluster Analysis on Time-Series Measurement of Plasma Cancer Antigen 15-3 in a Patient with Metastatic Breast Cancer
Abstract
Cancer Antigen 15-3 (CA 15-3) is a glycoprotein often linked to breast cancer. Elevated levels of CA 15-3, above the normal reference range of 30 U/mL (units per milliliter), are frequently found in the blood of patients with metastatic breast cancer, where the cancer has spread to other parts of the body, such as the bones. This study examines the importance of cluster analysis in evaluating time-series measurements of plasma CA 15-3 in a male patient with metastatic breast cancer that has spread to the trochanteric region. Clustering is a statistical method used to organize data based on similarity, though it may not directly reflect underlying physical properties. The trend of CA 15-3 time-series measurement presented here is familiar to oncologists. The novelty of this study lies in evaluating the significance of applying cluster analysis to the specific time-series data. The results indicate that this approach is indeed meaningful. Notably, two distinct clusters were identified within the data, as anticipated. The first cluster corresponds to the period before the recurrence of illness (metastatic breast cancer), while the second cluster reflects the advanced (metastatic) stage of the disease. The boundary between these clusters provides valuable insights into the onset of the metastatic stage. To our knowledge, this is the first study to apply cluster analysis to CA 15-3 time-series data. The results are promising. Its potential use in identifying the onset of the metastatic stage merits further examination.
