Cookies on this website

We use cookies to ensure that we give you the best experience on our website. If you click 'Accept all cookies' we'll assume that you are happy to receive all cookies and you won't see this message again. If you click 'Reject all non-essential cookies' only necessary cookies providing core functionality such as security, network management, and accessibility will be enabled. Click 'Find out more' for information on how to change your cookie settings.

I. INTRODUCTION When a patient is found to have cancer, there are three main concerns which are translated into crucial questions for the clinician. He/she wants to know how (1) serious the disease is, i.e., how life threatening it is; (2) what the best treatment is with its potential deleterious effects; and (3) the prognosis with or without treatment. Whilst with many cancers there is a first choice treatment and the ideal course of action is clear, for other malignancies, particularly in urology - e.g., certain grades and stages of prostate and bladder cancer - treatment decisions are more difficult. Decisions are made usually on the basis of conventional information such as tumour grade, stage, age and co-morbidity, statistical probabilities of disease progression, and an informed discussion between the treating clinician and the patient. For instance, if a man is diagnosed with low-grade and low-stage prostate cancer and he is told that he has a 10-15% risk of progression over a period of 10 years, the clinician is unable to predict exactly which side of the risk fence the patient will fall into. The consequence of such uncertainties could therefore be either overtreatment or undertreatment with their sequelae. Patients with such cancers would benefit greatly from any new methods of predicting outcome that will help them in selecting their treatment, which would be offered with a greater degree of confidence by the physician.



Book title

Artificial Neural Networks in Cancer Diagnosis, Prognosis, and Patient Management

Publication Date



125 - 132