Predicting IVF Outcome: A Proposed Web-based System Using Artificial Intelligence.
Siristatidis C., Vogiatzi P., Pouliakis A., Trivella M., Papantoniou N., Bettocchi S.
AIM: To propose a functional in vitro fertilization (IVF) prediction model to assist clinicians in tailoring personalized treatment of subfertile couples and improve assisted reproduction outcome. MATERIALS AND METHODS: Construction and evaluation of an enhanced web-based system with a novel Artificial Neural Network (ANN) architecture and conformed input and output parameters according to the clinical and bibliographical standards, driven by a complete data set and "trained" by a network expert in an IVF setting. RESULTS: The system is capable to act as a routine information technology platform for the IVF unit and is capable of recalling and evaluating a vast amount of information in a rapid and automated manner to provide an objective indication on the outcome of an artificial reproductive cycle. CONCLUSION: ANNs are an exceptional candidate in providing the fertility specialist with numerical estimates to promote personalization of healthcare and adaptation of the course of treatment according to the indications.