This research aims to develop a diagnostic tool that can quickly and accurately detect prostate cancer using electronic nose technology and a neural network trained on a dataset of urine samples from patients diagnosed with both prostate cancer and benign prostatic hyperplasia, which incorporates a unique data redundancy method. By analyzing signals from these samples, we were able to significantly reduce the number of unnecessary biopsies and improve the classification method, resulting in a recall rate of 91% for detecting prostate cancer. The goal is to make this technology widely available for use in primary care centers, to allow for rapid and non-invasive diagnoses.
Keywords: Deep learning; MOOSY-32; Machine intelligence; Neural networks; Prostate cancer; e-Nose.
© 2023. BioMed Central Ltd., part of Springer Nature.