1. Personalized prediction of first-cycle in vitro fertilization success
Bokyung Choi, Ph.D., Ernesto Bosch, M.D., Benjamin M. Lannon, M.D., Marie-Claude Leveille, Ph.D., Wing H. Wong, Ph.D., Arthur Leader, M.D., Antonio Pellicer, M.D., Alan S. Penzias, M.D., Mylene W.M. Yao, M.D. 
Fertility and Sterility 
Volume 99, Issue 7, Pages (June 2013)
DOI: /j.fertnstert
Copyright © 2013 American Society for Reproductive Medicine Terms and Conditions

2. Figure 1
Clinical data sources, datasets, and prediction model design used to generate and validate PreIVF-Diversity (PreIVF-D), a prediction model that predicts the probability of live birth with a patient's first IVF treatment. Outcomes data on first IVF cycles were extracted from deidentified data sets provided by three clinics: Boston IVF (BIVF; red), Instituto Valenciano de Infertilidad (IVI; blue), and Ottawa Fertility Centre (OFC; green). N indicates the number of IVF treatments. After applying inclusion and exclusion criteria, outcomes data from eligible cycles were used to generate clinic-specific prediction models (ovals), which were each decomposed to model components (circles) (patent pending). Using a training set, PreIVF-D (oval) was generated by selecting model components from all three clinics. PreIVF-D was validated by testing on the independent data set comprising data from all three clinics: training and independent test datasets (pale orange).
Fertility and Sterility  , DOI: ( /j.fertnstert )
Copyright © 2013 American Society for Reproductive Medicine Terms and Conditions