Knowledge discovery in an infertility database using artificial neural networks

Databases are complex structures that may conceal implicit patterns of information that cannot be easily discovered by conventional analysis and interrogation methods. This situation can be exacerbated as the database grows in size, and the data therein grows in complexity. Discovery of patterns and trends in such cases requires database query methods far in advance of those traditionally used. Such databases may be analysed using a set of techniques often collectively referred to as knowledge discovery. This paper describes the use of neural network techniques used in an ongoing knowledge discovery exercise applied to one such database. The ovulation induction infertility database at the Jessop Hospital, Sheffield, holds details of patients treated with gonadotrophins for ovulation induction. The data held is multidimensional in nature, and is of a level of complexity such that it is currently very difficult to predict, with any degree of certainty, the outcome of a particular treatment cycle (i.e. the probability of a patient becoming pregnant).