Evaluating the Diagnostic Potential of Biomarker Panels in Breast Cancer and Prostate Adenocarcinoma

Sep 23, 2026

Upload by Jake

Noninvasive diagnostic methods are crucial for early cancer detection and improved outcomes, yet the best biomarker panels for accurate diagnosis are still unclear. This study assesses the diagnostic performance of 12 plasma biomarkers in separating breast cancer and prostate adenocarcinoma patients from healthy controls. Using ELISA quantification, statistical testing, and random forest machine learning, the work identifies significantly elevated markers and demonstrates strong classification potential, while highlighting redundancy that requires panel optimization.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages8

Reading Time20 min

AccessFree to download

Abstract

Background

Materials and Methods

Results

Conclusion

Introduction

Abbreviations

Health Science Reports |
ORIGINAL RESEARCH
Evaluating the Diagnostic Potential of Biomarker Panels in Breast Cancer and Prostate Adenocarcinoma
Kldiashvili Ekaterina1 | Iordanishvili Saba1,2 | Adamia Sophia2 | Abiatari Ivane2 | Zarnadze Maia1
1Petre Shotadze Tbilisi Medical Academy, Tbilisi, Georgia | 2Institute of Medical and Public Health Research, Ilia State University, Tbilisi, Georgia Correspondence: Kldiashvili Ekaterina ([e.kldiashvili@tma.edu.ge](e.kldiashvili@tma.edu.ge))
Received: 23 December 2024 | Revised: 27 March 2025 | Accepted: 16 April 2025
Funding: This study was supported by the Shota Rustaveli National Science Foundation of Georgia (FR‐19‐24458) .
Keywords: biomarkers | blood samples | cancer | machine learning | panel | | | --- | --- | | ABSTRACT
Background: Noninvasive diagnostic methods are essential for early cancer detection and improved patient outcomes. Circulating biomarkers, measurable indicators of pathological processes, offer a promising avenue, yet optimal panels for reliable cancer diagnosis remain undefined. This study evaluates the diagnostic performance of selected plasma biomarkers in distinguishing breast cancer and prostate adenocarcinoma patients from healthy individuals, using statistical analysis and machine learning.
Materials and Methods: We analyzed blood samples from 162 participants (73 cancer patients: 51 with breast cancer and 22 with prostate adenocarcinoma; 89 healthy controls) . Levels of 12 cancer‐associated biomarkers—including Ki67, DNMT1, BRCA1, and MPO—were quantified using enzyme‐linked immunosorbent assays (ELISA) . Statistical analyses, including the Mann–Whitney U test and machine learning models (random forest), were employed to assess the predictive accuracy of these biomarkers in distinguishing between cancerous and healthy states.
Results: Biomarkers such as Ki67, DNMT1, and MPO were significantly elevated in cancer groups. Random forest models using selected combinations (e.g., BRCA1‐CTA‐TP53) achieved perfect classification accuracy (AUC = 1.00) . However, high inter‐marker correlations suggested potential redundancy, underscoring the need for biomarker panel optimization. Conclusion: Our findings support the potential of biomarker panels for accurate, noninvasive cancer diagnostics. Further validation in larger, more diverse cohorts is warranted to establish clinical utility and generalizability. | | | 1 | Introduction | while effective, are invasive, time‐consuming, and may delay treatment initiation [3, 4] . In recent years, circulating | | Cancer has seen remarkable advancements, with breast and | biomarkers—measurable molecules in blood or other body | | prostate cancers among the most frequently diagnosed ma- | fluids—have emerged as a promising alternative for non- | | lignancies in women and men, respectively [1, 2] . Despite | invasive cancer diagnostics [5–7] . Biomarkers, such as Ki67, | | advances in treatment, early detection remains a critical | BRCA1, and DNMT1 are associated with tumor proliferation, | | determinant of prognosis and survival. Current diagnostic | DNA repair dysfunction, and epigenetic changes that are | | methods often rely on imaging or tissue biopsies, which, | central to oncogenesis [8–10] . However, many individual | | Abbreviations: AUC‐ROC, area under the receiver operating characteristic curve; BRCA1, breast cancer type 1 susceptibility protein; CA15.3, cancer antigen 15‐3; CEA, carcinoembryonic antigen; CTA, cancer/testis antigen; DNMT1, DNA methyltransferase 1; ELISA, enzyme‐linked immunosorbent assay; FOXP3, forkhead box P3; Ki67, a cellular marker for proliferation; miRNA, microRNA; MPO, myeloperoxidase; NIR, no information rate; PDCD1LG2, programmed cell death 1 ligand 2; SD, standard deviation; TP53, tumor protein 53; TP63, tumor protein 63 . | | | This is an open access article under the terms of the Creative Commons Attribution‐NonCommercial‐NoDerivs License, which permits u

FAQs

Why are biomarker panels important for cancer diagnosis?

They aim to provide reliable noninvasive detection by combining multiple measurable blood indicators, which may outperform single markers with limited sensitivity or specificity.

What methods were used to evaluate the biomarkers?

Plasma biomarker levels were measured by ELISA, followed by statistical analyses and random forest machine learning to assess predictive accuracy and classification performance.

Which biomarkers showed significant differences between cancer patients and healthy controls?

Ki67, DNMT1, and MPO were significantly elevated in cancer groups compared with healthy controls.

Sep 23, 2026

Upload by Jake