Machine Learning Models for Prostate Cancer Identification

Elias Dritsas, Maria Trigka, Phivos Mylonas

2023

Abstract

In the present research paper, we focused on prostate cancer identification with machine learning (ML) techniques and models. Specifically, we approached the specific disease as a 2-class classification problem by categorizing patients based on tumour type as benign or malignant. We applied the synthetic minority over-sampling technique (SMOTE) in our ML models in order to reveal the model with the best predictive ability for our purpose. After the experimental evaluation, the Rotation Forest (RotF) model overcame the others, achieving an accuracy, precision, recall, and f1-score of 86.3%, and an AUC equal to 92.4% after SMOTE with 10-fold cross-validation.

Paper Citation

in Harvard Style

Dritsas E., Trigka M. and Mylonas P. (2023). Machine Learning Models for Prostate Cancer Identification. In Proceedings of the 15th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR; ISBN 978-989-758-671-2, SciTePress, pages 421-428. DOI: 10.5220/0012236800003598

in Bibtex Style

@conference{kdir23,
author={Elias Dritsas and Maria Trigka and Phivos Mylonas},
title={Machine Learning Models for Prostate Cancer Identification},
booktitle={Proceedings of the 15th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR},
year={2023},
pages={421-428},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012236800003598},
isbn={978-989-758-671-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR
TI - Machine Learning Models for Prostate Cancer Identification
SN - 978-989-758-671-2
AU - Dritsas E.
AU - Trigka M.
AU - Mylonas P.
PY - 2023
SP - 421
EP - 428
DO - 10.5220/0012236800003598
PB - SciTePress