Healthcare

Abstract Prostate cancer is the most common malignancy affecting men and thesecond-leading cause of cancer death in the US. To detect and classify the risk of prostate cancer, doctors perform screening of prostate-specific antigen (PSA) levels. In this Thesis we want to improve thisrisk classification with unsupervised machine learning methods, as thelabels of cancer or no cancer may not reflect the truth; given that canceris only considered as such after confirmation by biopsy and thus possi-bly leaving some patients with cancer with the wrong label.

Abstract Cancer detection is one of the leading research topics in medical science. Whetherit is breast, lung, brain, or prostate cancer, progress is being made to improve theaccuracy and timing of detection. Prostate cancer is the second most commoncancer in men and the sixth leading cause of cancer death among men in the world.Many prostate cancers are indolent and do not result in cancer mortality, evenwithout treatment. However, a significant percentage of prostate cancer patientshave aggressive cancers that rapidly progress to metastatic disease and are oftendangerous.