Towards Unsupervised Learning Driven Intelligence for Prediction of Prostate Cancer

Abstract

Prostate cancer is a widespread and global disease which affects adult males – it is said that key causes of the cancer include age, family history, and ethnicity. In this study, the Kaggle prostate cancer dataset, comprising of data from 100 patients with a mixture that both had cancer and did not have cancer, was used alongside machine learning prediction models for the design of unsupervised and automated intelligent systems for the prediction of prostate cancer. Two intelligent systems were designed and underpinned by unsupervised learning algorithms, namely fuzzy c-means and agglomerative hierarchical clustering, where the various intelligent systems were able to make a prostate cancer prediction with accuracies of over 80% for the various classification metrics, alongside being able to predict an associated stage of the prostate cancer. Both designed intelligent systems offer a complimentary alternative to each other, and their relative merits are discussed in the paper.

Received: 1 December 2023 | Revised: 7 April 2024 | Accepted: 5 July 2024

Conflicts of Interest

The author declares that he has no conflicts of interest to this work.

Data Availability Statement

Data is available on request from the corresponding author upon reasonable request.

Author Contribution Statement

Ejay Nsugbe: Conceptualization, Methodology, Software, Validation, Formal analysis, Investigation, Resources, Data curation, Writing - original draft, Writing - review & editing, Visualization, Supervision, Project administration.